Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55f65037e559ae103976d9bc890cdb1b91591271aae6c76c58482439aee28fad
+oid sha256:2534a08c7850aa9f2b967cbf92833aada651e02730033fed5a0c4f1c98e38032
 size 323014168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7900fce10731ad960de536a3f80d6f1a3031b2fd8371771faa6247cd3b427e9e
+oid sha256:ce8c2ed232c17c913ee9d7dc60dde2ad778ba27808b513f44911c2169d5e1fcc
 size 646253418

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ccc88b993320ef8bd5ed675b4a14b0aad98b752c0f63437c51a718a9bf12712f
+oid sha256:c7bb80daa60e56eaa2cb7494826d9903a45bac3aafa66ee2769ba5951c1f5c95
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2da438a69b0760f3edc5516adc6076a6edb5926e57e1907d29ef7741c0beea82
+oid sha256:f18dc0299e950ce7215c2cbe87a9ffa9e28f7d96a6bde7c5732db41c864bdf95
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3dc7450e3fc20f5e3d5ed8bc949cef7bc208ac71f95b8157594ba7d037ad372a
+oid sha256:70639ef0c861e5fed9dc0c060800b69ba0680e56790e3b56610977642cdaab87
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:897c5ac763e061d7d59aa33902a576abf75ac89c334cb708ec12e0024aa994dc
+oid sha256:68f79fadaf80143ece5e703cdf430fed544e4ea5104c20978b82d209b531c89e
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d271cdb95f63cd655315f063ca2e25c78dc5ae4275523c5d4f80f367586b3351
+oid sha256:5607f6de446164d9d9adb8b91c44cec55b14aa391e24ba5637c08b834eedda2a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.8139303922653198,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.006403996093562383,
+  "best_metric": 1.8088456392288208,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.012807992187124766,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 12.292,
       "eval_steps_per_second": 3.196,
       "step": 25
+    },
+    {
+      "epoch": 0.006660155937304878,
+      "grad_norm": 0.09742273390293121,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 1.417,
+      "step": 26
+    },
+    {
+      "epoch": 0.006916315781047374,
+      "grad_norm": 0.10393131524324417,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 1.5609,
+      "step": 27
+    },
+    {
+      "epoch": 0.0071724756247898685,
+      "grad_norm": 0.10253896564245224,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 1.651,
+      "step": 28
+    },
+    {
+      "epoch": 0.007428635468532364,
+      "grad_norm": 0.11944159120321274,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 1.707,
+      "step": 29
+    },
+    {
+      "epoch": 0.007684795312274859,
+      "grad_norm": 0.12614507973194122,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 1.7486,
+      "step": 30
+    },
+    {
+      "epoch": 0.007940955156017355,
+      "grad_norm": 0.1243036687374115,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 1.8394,
+      "step": 31
+    },
+    {
+      "epoch": 0.00819711499975985,
+      "grad_norm": 0.12516279518604279,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 1.8951,
+      "step": 32
+    },
+    {
+      "epoch": 0.008453274843502346,
+      "grad_norm": 0.13885308802127838,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 1.9785,
+      "step": 33
+    },
+    {
+      "epoch": 0.008709434687244841,
+      "grad_norm": 0.12817367911338806,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 1.9856,
+      "step": 34
+    },
+    {
+      "epoch": 0.008965594530987336,
+      "grad_norm": 0.12321033328771591,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 1.9968,
+      "step": 35
+    },
+    {
+      "epoch": 0.009221754374729831,
+      "grad_norm": 0.14202013611793518,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 2.0548,
+      "step": 36
+    },
+    {
+      "epoch": 0.009477914218472328,
+      "grad_norm": 0.20923654735088348,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 1.9868,
+      "step": 37
+    },
+    {
+      "epoch": 0.009734074062214822,
+      "grad_norm": 0.09520645439624786,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 1.3998,
+      "step": 38
+    },
+    {
+      "epoch": 0.009990233905957317,
+      "grad_norm": 0.08575084805488586,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 1.5252,
+      "step": 39
+    },
+    {
+      "epoch": 0.010246393749699812,
+      "grad_norm": 0.08441535383462906,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 1.6169,
+      "step": 40
+    },
+    {
+      "epoch": 0.010502553593442309,
+      "grad_norm": 0.09202511608600616,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 1.6491,
+      "step": 41
+    },
+    {
+      "epoch": 0.010758713437184804,
+      "grad_norm": 0.10047546029090881,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 1.7339,
+      "step": 42
+    },
+    {
+      "epoch": 0.011014873280927298,
+      "grad_norm": 0.10672976821660995,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 1.8578,
+      "step": 43
+    },
+    {
+      "epoch": 0.011271033124669793,
+      "grad_norm": 0.11075907200574875,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 1.8289,
+      "step": 44
+    },
+    {
+      "epoch": 0.01152719296841229,
+      "grad_norm": 0.11539074778556824,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 1.9278,
+      "step": 45
+    },
+    {
+      "epoch": 0.011783352812154785,
+      "grad_norm": 0.1180633008480072,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 1.9527,
+      "step": 46
+    },
+    {
+      "epoch": 0.01203951265589728,
+      "grad_norm": 0.11752723902463913,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 2.049,
+      "step": 47
+    },
+    {
+      "epoch": 0.012295672499639775,
+      "grad_norm": 0.12545828521251678,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 2.0189,
+      "step": 48
+    },
+    {
+      "epoch": 0.012551832343382271,
+      "grad_norm": 0.14639462530612946,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 2.0686,
+      "step": 49
+    },
+    {
+      "epoch": 0.012807992187124766,
+      "grad_norm": 0.2590751647949219,
+      "learning_rate": 1e-05,
+      "loss": 2.0232,
+      "step": 50
+    },
+    {
+      "epoch": 0.012807992187124766,
+      "eval_loss": 1.8088456392288208,
+      "eval_runtime": 4.0716,
+      "eval_samples_per_second": 12.28,
+      "eval_steps_per_second": 3.193,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.812907666370724e+17,
+  "total_flos": 5.624936571695268e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null