Training in progress, step 12000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef77a091d99ff91eba75355ced068d82754fe09197e0fe3fb0024d4681e880cd
+oid sha256:8551f34b08110ae0409b8440d3c6aebe368ed8d3db002ee5351bf9102cc149c5
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13d127c8a77b3a6f121a1e1766bf489c05dc85af0fb609f9d0474c53a6bbc073
+oid sha256:cfd2de65b175040f5da9800eea2d0dc2b6a4d304b142893b8d0191497fd8ada1
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:657e8f4565cffd7e4abf75f56b2fdcd3ae235671ae9b5c722c485957c12a53d9
+oid sha256:2d27d7df73326e1c0aee717403c0adf323847184edf4276ba1b5631d4a53dd69
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41e2a369098bdc7bbbac32b35b2de9650fe514b2c352f9f563c5554da15cddf2
+oid sha256:e235e460f5bdfcaf65cc8c31e1e3b2c2350fb2d33d9a604b0cf64e4a8cef95de
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.08207839727401733,
-  "best_model_checkpoint": "./fine-tuned/checkpoint-11500",
-  "epoch": 1.8399999999999999,
+  "best_metric": 0.08194975554943085,
+  "best_model_checkpoint": "./fine-tuned/checkpoint-12000",
+  "epoch": 1.92,
   "eval_steps": 500,
-  "global_step": 11500,
+  "global_step": 12000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1801,6 +1801,84 @@
       "eval_samples_per_second": 17.13,
       "eval_steps_per_second": 2.141,
       "step": 11500
+    },
+    {
+      "epoch": 1.8479999999999999,
+      "grad_norm": 5619.83984375,
+      "learning_rate": 1.152e-05,
+      "loss": 0.0563,
+      "step": 11550
+    },
+    {
+      "epoch": 1.8559999999999999,
+      "grad_norm": 92426.8046875,
+      "learning_rate": 1.144e-05,
+      "loss": 0.0588,
+      "step": 11600
+    },
+    {
+      "epoch": 1.8639999999999999,
+      "grad_norm": 7583.005859375,
+      "learning_rate": 1.136e-05,
+      "loss": 0.0559,
+      "step": 11650
+    },
+    {
+      "epoch": 1.8719999999999999,
+      "grad_norm": 6395.92578125,
+      "learning_rate": 1.128e-05,
+      "loss": 0.0552,
+      "step": 11700
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 9939.912109375,
+      "learning_rate": 1.1200000000000001e-05,
+      "loss": 0.0523,
+      "step": 11750
+    },
+    {
+      "epoch": 1.888,
+      "grad_norm": 5679.93212890625,
+      "learning_rate": 1.112e-05,
+      "loss": 0.0585,
+      "step": 11800
+    },
+    {
+      "epoch": 1.896,
+      "grad_norm": 6536.05419921875,
+      "learning_rate": 1.104e-05,
+      "loss": 0.0533,
+      "step": 11850
+    },
+    {
+      "epoch": 1.904,
+      "grad_norm": 7333.63330078125,
+      "learning_rate": 1.096e-05,
+      "loss": 0.0566,
+      "step": 11900
+    },
+    {
+      "epoch": 1.912,
+      "grad_norm": 7345.85009765625,
+      "learning_rate": 1.0880000000000001e-05,
+      "loss": 0.0555,
+      "step": 11950
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 21337.044921875,
+      "learning_rate": 1.08e-05,
+      "loss": 0.0576,
+      "step": 12000
+    },
+    {
+      "epoch": 1.92,
+      "eval_loss": 0.08194975554943085,
+      "eval_runtime": 116.8029,
+      "eval_samples_per_second": 17.123,
+      "eval_steps_per_second": 2.14,
+      "step": 12000
     }
   ],
   "logging_steps": 50,
@@ -1820,7 +1898,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.602412593152e+16,
+  "total_flos": 5.845995749376e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null