Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:498b313b112e641ca60d6a0471c8d89ac2e410a21f0b1ce4f3b0b44fc26be20c
+oid sha256:20bb86ab3d419301df827324402ab85ca4c2a36fbaab2c4cb3493cc8339b4072
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75fd9583f961e41d56539ce0328900153de719aa49b85b58113428b774724494
+oid sha256:14336e1c2b7b105ef4f2253f24000a0607ef6bf369147feee5d356b776e683db
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b1f7e74c92417dc92a8539c0a584056c35b4274a3fb049888a84cd57047e99c
+oid sha256:0a13307056da4bbb211ad48ade25632cd037a6f559d3df7d1e4eebdbef92276c
 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": 0.00013840032293408684,
+  "epoch": 0.0002768006458681737,
   "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": 26.161,
       "eval_steps_per_second": 13.082,
       "step": 3
+    },
+    {
+      "epoch": 0.0001845337639121158,
+      "grad_norm": 0.5888237953186035,
+      "learning_rate": 8e-05,
+      "loss": 0.8853,
+      "step": 4
+    },
+    {
+      "epoch": 0.00023066720489014475,
+      "grad_norm": 0.5911535024642944,
+      "learning_rate": 0.0001,
+      "loss": 0.7564,
+      "step": 5
+    },
+    {
+      "epoch": 0.0002768006458681737,
+      "grad_norm": 0.6763503551483154,
+      "learning_rate": 0.00012,
+      "loss": 0.913,
+      "step": 6
+    },
+    {
+      "epoch": 0.0002768006458681737,
+      "eval_loss": 0.8399578332901001,
+      "eval_runtime": 349.1528,
+      "eval_samples_per_second": 26.14,
+      "eval_steps_per_second": 13.072,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 647358761140224.0,
+  "total_flos": 1294717522280448.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null