Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36aec3378e5b3164d2ef918315ee3fb05e1a6d2bdb20e4f76c6bc9c2419fa668
+oid sha256:1065e1edc7dfa1ea0652e6c22a7fcabe5753599dd16bdfd4abceac9346eae98f
 size 2185308216

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41a2c147cc06dbadf24e39992a66c247dd677ef5e844dc2ada4bbcb7779fa138
+oid sha256:a1189ac361379cf7527ffdfeaa884b476bc4c87c4109aa7d154c5b84b52f6399
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b1f7e74c92417dc92a8539c0a584056c35b4274a3fb049888a84cd57047e99c
+oid sha256:1b6f8a1da0f85e008fb4827fcbbca87a735208d7dabb21326efc77740c3e1ecf
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
+oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 7.530309495720274e-05,
+  "epoch": 0.00015060618991440548,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 23.485,
       "eval_steps_per_second": 11.743,
       "step": 3
+    },
+    {
+      "epoch": 0.00010040412660960366,
+      "grad_norm": 1.4657057523727417,
+      "learning_rate": 8e-05,
+      "loss": 2.0341,
+      "step": 4
+    },
+    {
+      "epoch": 0.00012550515826200456,
+      "grad_norm": 0.9188522696495056,
+      "learning_rate": 0.0001,
+      "loss": 1.4815,
+      "step": 5
+    },
+    {
+      "epoch": 0.00015060618991440548,
+      "grad_norm": 2.8464882373809814,
+      "learning_rate": 0.00012,
+      "loss": 2.3255,
+      "step": 6
+    },
+    {
+      "epoch": 0.00015060618991440548,
+      "eval_loss": 3.5286591053009033,
+      "eval_runtime": 714.9036,
+      "eval_samples_per_second": 23.465,
+      "eval_steps_per_second": 11.733,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 647347839172608.0,
+  "total_flos": 1340934809714688.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null