Training in progress, step 9500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2d552abe54bc8b78698f085328cba7d4ca9faffbe5c176d69ae6298a741dc1f
+oid sha256:1e166df977f21f4e74668f730deac309df6a571f19acaa0dfa89c2e3c2819431
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23a4a556c668ac483f251fb2542a9567fdbeee24015d2afebd6c40ac1db320d9
+oid sha256:9e99baec34b5da3301e09eb5c4f9d3ef873b304cf96feddd1cfe61690f168589
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d44945f90b9153cb2a69f9475450a2111e7f4db9372411c8f14f263baffa58d1
+oid sha256:91f8e7f84c942f83f5d877ebb335efd09f2d70c83c135e4e031bf84b0af23af9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5115d8af133b4318a75821bef26ae5de84c140c9bd70b7ac727a7737d85cfbd6
+oid sha256:7e8e6e071a0a58044a0e6d93d2bb93dd252e4dfa6d5810853dc9dadf39da6ab9
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.08268450945615768,
-  "best_model_checkpoint": "./fine-tuned/checkpoint-9000",
-  "epoch": 1.44,
+  "best_metric": 0.08252418041229248,
+  "best_model_checkpoint": "./fine-tuned/checkpoint-9500",
+  "epoch": 1.52,
   "eval_steps": 500,
-  "global_step": 9000,
+  "global_step": 9500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1411,6 +1411,84 @@
       "eval_samples_per_second": 17.12,
       "eval_steps_per_second": 2.14,
       "step": 9000
+    },
+    {
+      "epoch": 1.448,
+      "grad_norm": 5681.900390625,
+      "learning_rate": 1.552e-05,
+      "loss": 0.0549,
+      "step": 9050
+    },
+    {
+      "epoch": 1.456,
+      "grad_norm": 5498.50048828125,
+      "learning_rate": 1.544e-05,
+      "loss": 0.0551,
+      "step": 9100
+    },
+    {
+      "epoch": 1.464,
+      "grad_norm": 7044.8017578125,
+      "learning_rate": 1.5360000000000002e-05,
+      "loss": 0.0557,
+      "step": 9150
+    },
+    {
+      "epoch": 1.472,
+      "grad_norm": 8311.8076171875,
+      "learning_rate": 1.528e-05,
+      "loss": 0.0559,
+      "step": 9200
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 10259.4189453125,
+      "learning_rate": 1.5200000000000002e-05,
+      "loss": 0.057,
+      "step": 9250
+    },
+    {
+      "epoch": 1.488,
+      "grad_norm": 7944.630859375,
+      "learning_rate": 1.5120000000000001e-05,
+      "loss": 0.0541,
+      "step": 9300
+    },
+    {
+      "epoch": 1.496,
+      "grad_norm": 9513.1875,
+      "learning_rate": 1.504e-05,
+      "loss": 0.0558,
+      "step": 9350
+    },
+    {
+      "epoch": 1.504,
+      "grad_norm": 6013.54296875,
+      "learning_rate": 1.4959999999999999e-05,
+      "loss": 0.0532,
+      "step": 9400
+    },
+    {
+      "epoch": 1.512,
+      "grad_norm": 7162.22314453125,
+      "learning_rate": 1.488e-05,
+      "loss": 0.0553,
+      "step": 9450
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 6351.9833984375,
+      "learning_rate": 1.48e-05,
+      "loss": 0.0548,
+      "step": 9500
+    },
+    {
+      "epoch": 1.52,
+      "eval_loss": 0.08252418041229248,
+      "eval_runtime": 116.7082,
+      "eval_samples_per_second": 17.137,
+      "eval_steps_per_second": 2.142,
+      "step": 9500
     }
   ],
   "logging_steps": 50,
@@ -1430,7 +1508,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.384496812032e+16,
+  "total_flos": 4.628079968256e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null