Training in progress, step 462, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c65f2723695d55c4676894a4cc573fa60c43c6f9d8e6b10a5f8338a48cb5495
+oid sha256:df0e540779c16a9c9b8e0788020851b763c6ccde82f230184c6995b221b6b636
 size 93608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d0f7e9bc2d46e8ee5840e716e44a1192336abc75f777e9c4ef214dc13e626af
+oid sha256:9d03b8186e15e8d8547427ceb0c67f3e312c09939c3148d3ddf48c2bbfe1bde0
 size 197158

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cdfe269170b74b584fdf82fb7f4fe475adef4c7006c041ed6cb8c1885b4ecaa
+oid sha256:c51931e2d3751996d51194bb17f4339acd99c19e556e5384d965eaa00841d426
 size 14244

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": 1.188118811881188,
+  "epoch": 1.306930693069307,
   "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": 92.516,
       "eval_steps_per_second": 11.642,
       "step": 420
+    },
+    {
+      "epoch": 1.1966053748231966,
+      "grad_norm": 0.09405164420604706,
+      "learning_rate": 5.9702234071631e-06,
+      "loss": 11.8103,
+      "step": 423
+    },
+    {
+      "epoch": 1.2050919377652052,
+      "grad_norm": 0.07892228662967682,
+      "learning_rate": 5.5226705990794155e-06,
+      "loss": 11.8166,
+      "step": 426
+    },
+    {
+      "epoch": 1.2135785007072135,
+      "grad_norm": 0.09944994747638702,
+      "learning_rate": 5.091571939329048e-06,
+      "loss": 11.8157,
+      "step": 429
+    },
+    {
+      "epoch": 1.222065063649222,
+      "grad_norm": 0.09870926290750504,
+      "learning_rate": 4.677086910538092e-06,
+      "loss": 11.8141,
+      "step": 432
+    },
+    {
+      "epoch": 1.2305516265912306,
+      "grad_norm": 0.16009728610515594,
+      "learning_rate": 4.279368849209381e-06,
+      "loss": 11.8126,
+      "step": 435
+    },
+    {
+      "epoch": 1.239038189533239,
+      "grad_norm": 0.10148247331380844,
+      "learning_rate": 3.898564888996476e-06,
+      "loss": 11.8173,
+      "step": 438
+    },
+    {
+      "epoch": 1.2475247524752475,
+      "grad_norm": 0.057802699506282806,
+      "learning_rate": 3.534815906272404e-06,
+      "loss": 11.8136,
+      "step": 441
+    },
+    {
+      "epoch": 1.256011315417256,
+      "grad_norm": 0.059853699058294296,
+      "learning_rate": 3.18825646801314e-06,
+      "loss": 11.8178,
+      "step": 444
+    },
+    {
+      "epoch": 1.2644978783592644,
+      "grad_norm": 0.11142271012067795,
+      "learning_rate": 2.8590147820153513e-06,
+      "loss": 11.8121,
+      "step": 447
+    },
+    {
+      "epoch": 1.272984441301273,
+      "grad_norm": 0.12580835819244385,
+      "learning_rate": 2.547212649466568e-06,
+      "loss": 11.8092,
+      "step": 450
+    },
+    {
+      "epoch": 1.2814710042432815,
+      "grad_norm": 0.09984395653009415,
+      "learning_rate": 2.2529654198854835e-06,
+      "loss": 11.8177,
+      "step": 453
+    },
+    {
+      "epoch": 1.28995756718529,
+      "grad_norm": 0.06916932761669159,
+      "learning_rate": 1.9763819484490355e-06,
+      "loss": 11.8155,
+      "step": 456
+    },
+    {
+      "epoch": 1.2984441301272984,
+      "grad_norm": 0.15921108424663544,
+      "learning_rate": 1.7175645557220566e-06,
+      "loss": 11.813,
+      "step": 459
+    },
+    {
+      "epoch": 1.306930693069307,
+      "grad_norm": 0.08516174554824829,
+      "learning_rate": 1.4766089898042678e-06,
+      "loss": 11.81,
+      "step": 462
+    },
+    {
+      "epoch": 1.306930693069307,
+      "eval_loss": 11.817733764648438,
+      "eval_runtime": 6.4426,
+      "eval_samples_per_second": 92.509,
+      "eval_steps_per_second": 11.641,
+      "step": 462
     }
   ],
   "logging_steps": 3,
@@ -1094,7 +1200,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2580649574400.0,
+  "total_flos": 2832537845760.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null