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:a1f1fde1ae0bed5857df3fe6f4659c178db0ed1d472e176c87a2faa93b44edbd
+oid sha256:226e6cddab68021edd0b62304807a0f388dd1e6ccac5a6281c78806b5f936c6d
 size 70430032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb38bd41c0cc559f6bededecd19a5e328f9b9dfbf5e889cee7c231e4b5aea61a
+oid sha256:03148b8f3588ea2c18f023d3e791f74ad30f392fa099746bebe5cc3e038d230b
 size 141053442

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60313a4685a15a506297f01b26dbf0f96af31aa866666b7a0124b9c94e667f14
+oid sha256:d6df374baea4348ce8ae8d750b2c37dac27e286302cc36dbaf858ccdab6834bb
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eca5f9e881a9e507111f06db5c73b1b26c632fa33b1dbe55aa87409a3baeb776
+oid sha256:19925da473ffd77e416843249050970eb0e8e8a9a4000627b3a7c9b2ff9f802d
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f33f77c0ca380a398a551fc621a93a76c1828366ec240a137e3ef9a52fc21bad
+oid sha256:a8568d885bcc3e33861d6c2c696cc90c7a48b8b9b9cd1a51deeeb516653797ba
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a35e2176da757595aad4064a6d46884630d1006088f462e6b8a9700386884ed0
+oid sha256:faca926cd464ae8e5c2a2423ccbdc6b8ad7787b80443eec91e0c1f1f1f8d5767
 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": null,
   "best_model_checkpoint": null,
-  "epoch": 0.33585222502099077,
+  "epoch": 0.6717044500419815,
   "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": 67.461,
       "eval_steps_per_second": 17.54,
       "step": 25
+    },
+    {
+      "epoch": 0.3492863140218304,
+      "grad_norm": 0.27871379256248474,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.9502,
+      "step": 26
+    },
+    {
+      "epoch": 0.36272040302267,
+      "grad_norm": 0.2754870057106018,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.9393,
+      "step": 27
+    },
+    {
+      "epoch": 0.37615449202350965,
+      "grad_norm": 0.24578134715557098,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.9144,
+      "step": 28
+    },
+    {
+      "epoch": 0.3895885810243493,
+      "grad_norm": 0.24544677138328552,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.9256,
+      "step": 29
+    },
+    {
+      "epoch": 0.40302267002518893,
+      "grad_norm": 0.2284000962972641,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.8907,
+      "step": 30
+    },
+    {
+      "epoch": 0.4164567590260285,
+      "grad_norm": 0.22578762471675873,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.9039,
+      "step": 31
+    },
+    {
+      "epoch": 0.42989084802686817,
+      "grad_norm": 0.21225938200950623,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.9315,
+      "step": 32
+    },
+    {
+      "epoch": 0.4433249370277078,
+      "grad_norm": 0.22618161141872406,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.8937,
+      "step": 33
+    },
+    {
+      "epoch": 0.45675902602854745,
+      "grad_norm": 0.24397031962871552,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.8986,
+      "step": 34
+    },
+    {
+      "epoch": 0.47019311502938704,
+      "grad_norm": 0.2503018081188202,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.9226,
+      "step": 35
+    },
+    {
+      "epoch": 0.4836272040302267,
+      "grad_norm": 0.23289993405342102,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.8954,
+      "step": 36
+    },
+    {
+      "epoch": 0.49706129303106633,
+      "grad_norm": 0.2558768689632416,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.8833,
+      "step": 37
+    },
+    {
+      "epoch": 0.5104953820319059,
+      "grad_norm": 0.22449778020381927,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.9091,
+      "step": 38
+    },
+    {
+      "epoch": 0.5239294710327456,
+      "grad_norm": 0.20541346073150635,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.9165,
+      "step": 39
+    },
+    {
+      "epoch": 0.5373635600335852,
+      "grad_norm": 0.20522888004779816,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.9178,
+      "step": 40
+    },
+    {
+      "epoch": 0.5507976490344249,
+      "grad_norm": 0.20278018712997437,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.9317,
+      "step": 41
+    },
+    {
+      "epoch": 0.5642317380352645,
+      "grad_norm": 0.20812608301639557,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.8763,
+      "step": 42
+    },
+    {
+      "epoch": 0.5776658270361041,
+      "grad_norm": 0.20340973138809204,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.8815,
+      "step": 43
+    },
+    {
+      "epoch": 0.5910999160369438,
+      "grad_norm": 0.20302090048789978,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.9081,
+      "step": 44
+    },
+    {
+      "epoch": 0.6045340050377834,
+      "grad_norm": 0.20221669971942902,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.8941,
+      "step": 45
+    },
+    {
+      "epoch": 0.617968094038623,
+      "grad_norm": 0.21326152980327606,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.8953,
+      "step": 46
+    },
+    {
+      "epoch": 0.6314021830394626,
+      "grad_norm": 0.20957252383232117,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.8796,
+      "step": 47
+    },
+    {
+      "epoch": 0.6448362720403022,
+      "grad_norm": 0.21854941546916962,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.9229,
+      "step": 48
+    },
+    {
+      "epoch": 0.6582703610411419,
+      "grad_norm": 0.2276400476694107,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.8743,
+      "step": 49
+    },
+    {
+      "epoch": 0.6717044500419815,
+      "grad_norm": 0.27538827061653137,
+      "learning_rate": 1e-05,
+      "loss": 0.938,
+      "step": 50
+    },
+    {
+      "epoch": 0.6717044500419815,
+      "eval_loss": 0.9089437127113342,
+      "eval_runtime": 0.7452,
+      "eval_samples_per_second": 67.098,
+      "eval_steps_per_second": 17.445,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -212,12 +395,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.47650456322048e+16,
+  "total_flos": 2.95300912644096e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null