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:fdfdf458b67a2c412c8c22db356d362e42d03649ba2d63e6dcb14697f761d509
+oid sha256:6a0bfe1cc814095700ec3f0b3bdc80051daf687d368353fe67425e6f543fba49
 size 101752088

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea1c4943ebbebd9c3f791bfb20c0cb39f3bd14e2474a46e497691c35cb81882a
+oid sha256:c6cd1eb4c61793a2c7309aef0a4b451526eeb4e9ff1638d0047137c59150395b
 size 52046596

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25cf6de4217912e3bfb2ff2f9c776a49a5c70644a3e19e79ad8543a9356c7753
+oid sha256:96d6c3490071a525ca6e5c4cd9f2685e5d3d363a4357eea800161a6e9da2c951
 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": 0.00022987184644560657,
+  "epoch": 0.00045974369289121313,
   "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": 5.83,
       "eval_steps_per_second": 2.915,
       "step": 3
+    },
+    {
+      "epoch": 0.00030649579526080876,
+      "grad_norm": 2.084083318710327,
+      "learning_rate": 8e-05,
+      "loss": 0.8819,
+      "step": 4
+    },
+    {
+      "epoch": 0.00038311974407601095,
+      "grad_norm": 1.8943278789520264,
+      "learning_rate": 0.0001,
+      "loss": 0.6412,
+      "step": 5
+    },
+    {
+      "epoch": 0.00045974369289121313,
+      "grad_norm": 1.8883026838302612,
+      "learning_rate": 0.00012,
+      "loss": 0.4795,
+      "step": 6
+    },
+    {
+      "epoch": 0.00045974369289121313,
+      "eval_loss": 0.3448009192943573,
+      "eval_runtime": 950.9924,
+      "eval_samples_per_second": 5.778,
+      "eval_steps_per_second": 2.89,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 987807602442240.0,
+  "total_flos": 1975615204884480.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null