Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:293a505639be021d462c0000cdcbb47c3a759edb55d3b2e2ced4be2a1d55f4ba
+oid sha256:fd04e9621a37984489166fa03530eb25f38cff9d76f989b6db9380eb5919e451
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8aee13d79d93a5cf2197020d503c3a59759a07a34bbc4b3263730c8a8daa0dc5
+oid sha256:7218c93378804e18f763bf31fa273e0d9f4f1e0843118ef2a867d8d7cd010e34
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:631dfb2aa9ae256eca5748a1b2ab04547dfc14e5e8346db748407ed5d049499d
+oid sha256:a68cd2a0196a6713af61a6a5ec57d388549ceab000d778970629ba70bc0f12ea
 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": 0.01011804384485666,
+  "epoch": 0.02023608768971332,
   "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": 32.421,
       "eval_steps_per_second": 16.34,
       "step": 3
+    },
+    {
+      "epoch": 0.013490725126475547,
+      "grad_norm": 0.8919812440872192,
+      "learning_rate": 8e-05,
+      "loss": 2.684,
+      "step": 4
+    },
+    {
+      "epoch": 0.016863406408094434,
+      "grad_norm": 1.456526279449463,
+      "learning_rate": 0.0001,
+      "loss": 3.4474,
+      "step": 5
+    },
+    {
+      "epoch": 0.02023608768971332,
+      "grad_norm": 1.1174732446670532,
+      "learning_rate": 0.00012,
+      "loss": 2.9132,
+      "step": 6
+    },
+    {
+      "epoch": 0.02023608768971332,
+      "eval_loss": 3.2028563022613525,
+      "eval_runtime": 3.8965,
+      "eval_samples_per_second": 32.08,
+      "eval_steps_per_second": 16.168,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 554869274443776.0,
+  "total_flos": 1109738548887552.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null