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:e54bb09f9c0a75ab367df7ebaa5656b8455df5d95c3ee08b2dcdee2e6dc002ac
+oid sha256:6e3dbb891655a04fde8f4c34e2d9a78d366b194ba8d510271c6af0c0a8a54dec
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d42b586c34aa3b8b8d4de788e81c9cda5b58c1fb8c6f4ef2e5073e634485e76d
+oid sha256:bbd638be155de95e94e322b5d90c8c4dbaabfdb76c02b5c870c66beb446d6364
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:631dfb2aa9ae256eca5748a1b2ab04547dfc14e5e8346db748407ed5d049499d
+oid sha256:a68cd2a0196a6713af61a6a5ec57d388549ceab000d778970629ba70bc0f12ea
 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": 5.850775959161584e-05,
+  "epoch": 0.00011701551918323167,
   "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": 31.117,
       "eval_steps_per_second": 15.558,
       "step": 3
+    },
+    {
+      "epoch": 7.801034612215445e-05,
+      "grad_norm": 21.161108016967773,
+      "learning_rate": 8e-05,
+      "loss": 12.9586,
+      "step": 4
+    },
+    {
+      "epoch": 9.751293265269307e-05,
+      "grad_norm": 21.10256576538086,
+      "learning_rate": 0.0001,
+      "loss": 13.3408,
+      "step": 5
+    },
+    {
+      "epoch": 0.00011701551918323167,
+      "grad_norm": 24.035612106323242,
+      "learning_rate": 0.00012,
+      "loss": 12.6553,
+      "step": 6
+    },
+    {
+      "epoch": 0.00011701551918323167,
+      "eval_loss": 2.9650354385375977,
+      "eval_runtime": 694.0893,
+      "eval_samples_per_second": 31.106,
+      "eval_steps_per_second": 15.553,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 525800935784448.0,
+  "total_flos": 1051601871568896.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null