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:feee2d941ea50baf9fc275f846bbb60722faf653eab34d10a17aa31dc44fb497
+oid sha256:552ead8879be2b48133d869c7d5267c2e13688dbd2beb7f3b02820a52881ae1b
 size 27024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d392ab1e51084cf1d48d058f5e5b271e64edc4a7fc1ef84e73d900d96b75d46
+oid sha256:a8e8a62d474db75840d84dde1c6ecff4e3fe167b2f7fabc62687c0de16d746a6
 size 63974

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:464e6cdff3f8548ba79ace3859c72e6b06d1e045e69932eb75c584ad0e8918c8
+oid sha256:e9b931b5fc0c1bd85ac8b5cf7dfdfe32425d1d78ecf18cf7fdcddc467f06765e
 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": 0.001724385687598793,
+  "epoch": 0.003448771375197586,
   "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": 403.602,
       "eval_steps_per_second": 202.076,
       "step": 3
+    },
+    {
+      "epoch": 0.0022991809167983907,
+      "grad_norm": 0.14821669459342957,
+      "learning_rate": 8e-05,
+      "loss": 10.401,
+      "step": 4
+    },
+    {
+      "epoch": 0.0028739761459979883,
+      "grad_norm": 0.17169639468193054,
+      "learning_rate": 0.0001,
+      "loss": 10.3765,
+      "step": 5
+    },
+    {
+      "epoch": 0.003448771375197586,
+      "grad_norm": 0.19555452466011047,
+      "learning_rate": 0.00012,
+      "loss": 10.3845,
+      "step": 6
+    },
+    {
+      "epoch": 0.003448771375197586,
+      "eval_loss": 10.402830123901367,
+      "eval_runtime": 1.8997,
+      "eval_samples_per_second": 385.849,
+      "eval_steps_per_second": 193.188,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 38792724480.0,
+  "total_flos": 77585448960.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null