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:f8e83faa389dfdcdcd07a250d14c9435ad7786844bb17b104d126d329b30166d
+oid sha256:43ad998a84dd61c21dab06ebb3b469b34dbcd6ee985c11d8c6c6cea12fde5e84
 size 1579352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f98ba16271ab95fe86077317cb70a950436a81e34b632bd2c7101cdc9da01a31
+oid sha256:03be65548da7290631f28223731e3817538c441336122bc3c39cdd52741c18d8
 size 857338

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9691002b57f3290282e19d9920bae8718005f180e15d093539dd4bb7daab1af3
+oid sha256:e511b972c396bd5ac07671d8be757f45bfe85b6eee968cfc163f5a6e683fab07
 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": 0.00132890365448505,
+  "epoch": 0.0026578073089701,
   "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": 257.104,
       "eval_steps_per_second": 128.687,
       "step": 3
+    },
+    {
+      "epoch": 0.0017718715393133999,
+      "grad_norm": 931.22802734375,
+      "learning_rate": 8e-05,
+      "loss": 57.8984,
+      "step": 4
+    },
+    {
+      "epoch": 0.0022148394241417496,
+      "grad_norm": 936.4315185546875,
+      "learning_rate": 0.0001,
+      "loss": 81.5504,
+      "step": 5
+    },
+    {
+      "epoch": 0.0026578073089701,
+      "grad_norm": 815.0882568359375,
+      "learning_rate": 0.00012,
+      "loss": 73.032,
+      "step": 6
+    },
+    {
+      "epoch": 0.0026578073089701,
+      "eval_loss": 20.045948028564453,
+      "eval_runtime": 3.807,
+      "eval_samples_per_second": 249.805,
+      "eval_steps_per_second": 125.034,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3322492747776.0,
+  "total_flos": 6644985495552.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null