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:eb69980cc662648f04da2651a280cb6f599395edcd28d291bd23af7cd757a12d
+oid sha256:e6163f042982e75779c199f6b2b158d8670064b2c7d82174ad1c816fc8d6242c
 size 33572288

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1daac1623530f941e96382c713dc2a7c21b1eb4e19868446653cb255cff0286
+oid sha256:632b154edcad557298796e69b74cff20326f7e6d35480c6eb8d916163b298446
 size 17190970

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:195d4c400c94c012e035f8ad146f414c04945c5ea9b6f10c156783198ebe3350
+oid sha256:f7cec7fa95fb16b09232bf47470bd56c852288bce7d205fc837860a8a1d8db12
 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": 0.006518196632265073,
+  "epoch": 0.013036393264530146,
   "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": 5.909,
       "eval_steps_per_second": 2.954,
       "step": 3
+    },
+    {
+      "epoch": 0.008690928843020097,
+      "grad_norm": 34.175010681152344,
+      "learning_rate": 8e-05,
+      "loss": 22.6822,
+      "step": 4
+    },
+    {
+      "epoch": 0.010863661053775122,
+      "grad_norm": 27.02315330505371,
+      "learning_rate": 0.0001,
+      "loss": 19.7116,
+      "step": 5
+    },
+    {
+      "epoch": 0.013036393264530146,
+      "grad_norm": 32.253116607666016,
+      "learning_rate": 0.00012,
+      "loss": 24.4795,
+      "step": 6
+    },
+    {
+      "epoch": 0.013036393264530146,
+      "eval_loss": 4.786070346832275,
+      "eval_runtime": 33.4731,
+      "eval_samples_per_second": 5.796,
+      "eval_steps_per_second": 2.898,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 540955694333952.0,
+  "total_flos": 1081911388667904.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null