Training in progress, step 462, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a07dee49d799c7c4e594b277793ea8c2c44a124a650537f11e3afe2258bf9b52
+oid sha256:6016a91738f92c509fae7473f3f57402eab9ca7b18809aca2dddebeccba1d5a6
 size 93608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8281e7a7c385c76306c3e004746a48faed6d6fc5dc06a058997a000d46c08896
+oid sha256:708965279644d8d6384f3966c9dcc4ba57135c188ef8f9cff896c2c0f7989c0a
 size 197158

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43b6f75817f48f21e99a60f7fdd4858dd8e6cf511942acb28532f05a198992fd
+oid sha256:a7da5cf41b2b745faed03773025a29a11348f4944822e03e49fca03431b28118
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c4bec5f2ca6548158d067a427656c807f869711b2091a276a7aca2125ea8d69
+oid sha256:41a883c860a264fc5a57d9f8e7a25458dde31e87fca349eec5d367e6dfcc9b75
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dec3fb92b10a22709bb248d99db74c3e5d2a3281e3681c398d8c43f78f024c67
+oid sha256:6289290891553c37ba97585b94e0d2ee9f0bd3342fa8e89b2d64a0012f2bb90f
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4d94cc971111c55703dacd86e4e6c559013000276fcee696a129b53ceb6f248
+oid sha256:c32238f7435ba76061ab976f9cfddd71a9091d21054b073cb9871615b3dd3904
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9507fdefdfac1d5dbc7a23a3aeb675b6dd3cc22a3762b7e85ff02a1c9c43105
+oid sha256:7b58b44a2d5024ddc12e64ead45d5d25c7fc985d9aaeb44c7bc3de9b8cf56f23
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.0979751796211628,
+  "epoch": 1.2077073807968648,
   "eval_steps": 42,
-  "global_step": 420,
+  "global_step": 462,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1075,6 +1075,112 @@
       "eval_samples_per_second": 775.161,
       "eval_steps_per_second": 24.355,
       "step": 420
+    },
+    {
+      "epoch": 1.1058131939908558,
+      "grad_norm": 0.022812234237790108,
+      "learning_rate": 5.9702234071631e-06,
+      "loss": 11.7508,
+      "step": 423
+    },
+    {
+      "epoch": 1.1136512083605488,
+      "grad_norm": 0.02215123549103737,
+      "learning_rate": 5.5226705990794155e-06,
+      "loss": 11.9357,
+      "step": 426
+    },
+    {
+      "epoch": 1.1214892227302418,
+      "grad_norm": 0.018271734938025475,
+      "learning_rate": 5.091571939329048e-06,
+      "loss": 12.0107,
+      "step": 429
+    },
+    {
+      "epoch": 1.1293272370999348,
+      "grad_norm": 0.018984654918313026,
+      "learning_rate": 4.677086910538092e-06,
+      "loss": 12.1886,
+      "step": 432
+    },
+    {
+      "epoch": 1.1371652514696278,
+      "grad_norm": 0.018601972609758377,
+      "learning_rate": 4.279368849209381e-06,
+      "loss": 11.6696,
+      "step": 435
+    },
+    {
+      "epoch": 1.1450032658393208,
+      "grad_norm": 0.0175609327852726,
+      "learning_rate": 3.898564888996476e-06,
+      "loss": 12.2369,
+      "step": 438
+    },
+    {
+      "epoch": 1.1528412802090138,
+      "grad_norm": 0.018267886713147163,
+      "learning_rate": 3.534815906272404e-06,
+      "loss": 11.3125,
+      "step": 441
+    },
+    {
+      "epoch": 1.1606792945787068,
+      "grad_norm": 0.018670443445444107,
+      "learning_rate": 3.18825646801314e-06,
+      "loss": 12.0095,
+      "step": 444
+    },
+    {
+      "epoch": 1.1685173089483998,
+      "grad_norm": 0.01578577049076557,
+      "learning_rate": 2.8590147820153513e-06,
+      "loss": 11.9352,
+      "step": 447
+    },
+    {
+      "epoch": 1.1763553233180928,
+      "grad_norm": 0.018620701506733894,
+      "learning_rate": 2.547212649466568e-06,
+      "loss": 11.819,
+      "step": 450
+    },
+    {
+      "epoch": 1.1841933376877858,
+      "grad_norm": 0.020687857642769814,
+      "learning_rate": 2.2529654198854835e-06,
+      "loss": 12.2251,
+      "step": 453
+    },
+    {
+      "epoch": 1.1920313520574788,
+      "grad_norm": 0.0191540215164423,
+      "learning_rate": 1.9763819484490355e-06,
+      "loss": 11.8286,
+      "step": 456
+    },
+    {
+      "epoch": 1.1998693664271718,
+      "grad_norm": 0.017804287374019623,
+      "learning_rate": 1.7175645557220566e-06,
+      "loss": 11.6918,
+      "step": 459
+    },
+    {
+      "epoch": 1.2077073807968648,
+      "grad_norm": 0.019628843292593956,
+      "learning_rate": 1.4766089898042678e-06,
+      "loss": 12.2151,
+      "step": 462
+    },
+    {
+      "epoch": 1.2077073807968648,
+      "eval_loss": 11.916607856750488,
+      "eval_runtime": 3.3257,
+      "eval_samples_per_second": 775.165,
+      "eval_steps_per_second": 24.355,
+      "step": 462
     }
   ],
   "logging_steps": 3,
@@ -1094,7 +1200,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8102606929920.0,
+  "total_flos": 8912506060800.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null