Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1868ad33b792029be55efcf5e7f673c92388b2d551f929096a2b6cc13c8dcb87
+oid sha256:4a94eb08eef20744ad4637c3a1e61412f8a41b6fe9150cc92162c525e25a34a2
 size 390888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a825bbfd4cf6dba24561a412d36e32e2d467dcf93003732f07e40dcf0534efb
+oid sha256:6d834bfadf2eb5515244c50864e337a64e7019bec455614f0b61c635f4615586
 size 819770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86b1d1c847833c161251571b388af565d36854d60391836c815a5c304e314a4b
+oid sha256:f89ee07fe03d1a05ba9f35a1ae7e0f887e7de2494b1948e33f324c76bd30d853
 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": 0.003157894736842105,
+  "epoch": 0.00631578947368421,
   "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": 98.596,
       "eval_steps_per_second": 49.298,
       "step": 3
+    },
+    {
+      "epoch": 0.004210526315789474,
+      "grad_norm": 7.153548717498779,
+      "learning_rate": 8e-05,
+      "loss": 10.7967,
+      "step": 4
+    },
+    {
+      "epoch": 0.005263157894736842,
+      "grad_norm": 6.634437084197998,
+      "learning_rate": 0.0001,
+      "loss": 9.9932,
+      "step": 5
+    },
+    {
+      "epoch": 0.00631578947368421,
+      "grad_norm": 5.807681083679199,
+      "learning_rate": 0.00012,
+      "loss": 10.1376,
+      "step": 6
+    },
+    {
+      "epoch": 0.00631578947368421,
+      "eval_loss": 10.382869720458984,
+      "eval_runtime": 4.3914,
+      "eval_samples_per_second": 91.088,
+      "eval_steps_per_second": 45.544,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 196675633152.0,
+  "total_flos": 393351266304.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null