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:fb352ea36bdfc830556132f7e3497a6f71bc5e4aed353955a27524002277c60d
+oid sha256:672a596865be35c94df536b15690e2e5028e017ffd67118a4f228d581c1f4ae7
 size 39256456

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d645e6239dfa1062249ecebefd37c13a74b2725b252352bb613ab9ba0e7a1bc5
+oid sha256:dfbb8c1a611df48707355f32ea1d030ef2a26fd4d908ee6bac59d7d2d347ccc8
 size 20632826

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a638e6bd4189d44eeac1f993292bbad8f48cdfa2af9dfd0362a0525bbf6d848
+oid sha256:ed657ca35a3b26ab39201e05f010d681b5d27ca2e383b370948911cf5bec9601
 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": 0.0007944389275074479,
+  "epoch": 0.0015888778550148957,
   "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": 39.91,
       "eval_steps_per_second": 19.955,
       "step": 3
+    },
+    {
+      "epoch": 0.001059251903343264,
+      "grad_norm": 1.2603070735931396,
+      "learning_rate": 8e-05,
+      "loss": 1.6498,
+      "step": 4
+    },
+    {
+      "epoch": 0.0013240648791790798,
+      "grad_norm": 1.1261543035507202,
+      "learning_rate": 0.0001,
+      "loss": 1.3465,
+      "step": 5
+    },
+    {
+      "epoch": 0.0015888778550148957,
+      "grad_norm": 1.2346397638320923,
+      "learning_rate": 0.00012,
+      "loss": 1.2569,
+      "step": 6
+    },
+    {
+      "epoch": 0.0015888778550148957,
+      "eval_loss": 1.4900404214859009,
+      "eval_runtime": 40.1043,
+      "eval_samples_per_second": 39.647,
+      "eval_steps_per_second": 19.823,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 269212786360320.0,
+  "total_flos": 513951683051520.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null