Training in progress, step 45, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a165fb02f9a3a4bf5c227dc64bde9957f7d973aad681dae8e8b211d4f5d1400c
+oid sha256:b6be4e281632c63b92fa5d5edd18e7ca954c0c33b78e3176cc998442208e3d84
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1430b0e939ea6e6eca903aa7902aa26cfd4e78beb03a4834c2deff932e024b1a
+oid sha256:7c7a079a0ab4dd29eec7e8d870e47356f2f52a2851b4dfee5d10a853fec52488
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab2ed981c27f8081d81d2039e0485e05b085c6f7d5fed74c55bf1d3c4164f221
+oid sha256:efb9ca876132dfc2200ae668af8d96116d67ae8fe0758644fefda8e5b6341153
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35e2941b1419d36fedcd8eb55488740cb386508ea401393ade4c1f5fd25ff6c8
+oid sha256:8074483b54111bf60815c86124b01e5486a0c97c3c0bcc7642d6609b17e4381b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.019561097866617763,
+  "epoch": 0.022006235099944985,
   "eval_steps": 34,
-  "global_step": 40,
+  "global_step": 45,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -303,6 +303,41 @@
       "learning_rate": 0.0001982973099683902,
       "loss": 1.2364,
       "step": 40
+    },
+    {
+      "epoch": 0.020050125313283207,
+      "grad_norm": 1.3894869089126587,
+      "learning_rate": 0.0001979409767601366,
+      "loss": 1.0156,
+      "step": 41
+    },
+    {
+      "epoch": 0.02053915275994865,
+      "grad_norm": 1.2144147157669067,
+      "learning_rate": 0.00019755119679804367,
+      "loss": 0.9838,
+      "step": 42
+    },
+    {
+      "epoch": 0.021028180206614098,
+      "grad_norm": 1.2613141536712646,
+      "learning_rate": 0.0001971281031916114,
+      "loss": 0.9763,
+      "step": 43
+    },
+    {
+      "epoch": 0.02151720765327954,
+      "grad_norm": 1.316279649734497,
+      "learning_rate": 0.00019667184042691875,
+      "loss": 1.0909,
+      "step": 44
+    },
+    {
+      "epoch": 0.022006235099944985,
+      "grad_norm": 1.4056583642959595,
+      "learning_rate": 0.00019618256431728194,
+      "loss": 1.2575,
+      "step": 45
     }
   ],
   "logging_steps": 1,
@@ -322,7 +357,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.7755816782200832e+17,
+  "total_flos": 1.9975293879975936e+17,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null