Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:477ed1f1c25226a958b514ea3df23d6ad48a57cf83724cdd5488fc86d01635c6
+oid sha256:dc6a8dafa41640c86d096f3188c2105aa5fafaca1d9d0a66f6f623ed6c59b837
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0532295abf65f1bd216dcbd99da8cbd2bb6242084d2dceb62844bfcf6facce2f
+oid sha256:54f3a8239f22213c5bc7f9dc019a5aec915242c573b4c04a5e468d5767bde1d1
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05531349f6e2487143a7251afc8a645033108171aa1d481234785012b46d00ef
+oid sha256:e7b14d0c915e2c4063f110f3dbec036a026b529b8820509b2913f154771be18b
 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": 0.0044411547002220575,
+  "epoch": 0.008882309400444115,
   "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": 18.119,
       "eval_steps_per_second": 9.091,
       "step": 3
+    },
+    {
+      "epoch": 0.005921539600296077,
+      "grad_norm": 0.46282222867012024,
+      "learning_rate": 8e-05,
+      "loss": 0.7392,
+      "step": 4
+    },
+    {
+      "epoch": 0.007401924500370096,
+      "grad_norm": 0.47253677248954773,
+      "learning_rate": 0.0001,
+      "loss": 0.8891,
+      "step": 5
+    },
+    {
+      "epoch": 0.008882309400444115,
+      "grad_norm": 0.4877263903617859,
+      "learning_rate": 0.00012,
+      "loss": 0.8255,
+      "step": 6
+    },
+    {
+      "epoch": 0.008882309400444115,
+      "eval_loss": 0.7716551423072815,
+      "eval_runtime": 15.7283,
+      "eval_samples_per_second": 18.12,
+      "eval_steps_per_second": 9.092,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1109738548887552.0,
+  "total_flos": 2219477097775104.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null