Training in progress, step 12500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8551f34b08110ae0409b8440d3c6aebe368ed8d3db002ee5351bf9102cc149c5
+oid sha256:3440c751a156d2ea034af88bf09257dd0a13e2135cfbb097e39dfddddef310fd
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfd2de65b175040f5da9800eea2d0dc2b6a4d304b142893b8d0191497fd8ada1
+oid sha256:f1457c08b9b3534e02e583e1c8e42d69598ca892990b039f5a31fe9230fe0935
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d27d7df73326e1c0aee717403c0adf323847184edf4276ba1b5631d4a53dd69
+oid sha256:4f0a30224aa29ff1d82dc265e86d4dfad17d2e9441b1e7410af0f89b7ac502d4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e235e460f5bdfcaf65cc8c31e1e3b2c2350fb2d33d9a604b0cf64e4a8cef95de
+oid sha256:b03c363c915c0dcfc4a0726bfa268bae9d4c39d40263aa6bcf80af31957091aa
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.08194975554943085,
-  "best_model_checkpoint": "./fine-tuned/checkpoint-12000",
-  "epoch": 1.92,
+  "best_metric": 0.08158940076828003,
+  "best_model_checkpoint": "./fine-tuned/checkpoint-12500",
+  "epoch": 2.0,
   "eval_steps": 500,
-  "global_step": 12000,
+  "global_step": 12500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1879,6 +1879,84 @@
       "eval_samples_per_second": 17.123,
       "eval_steps_per_second": 2.14,
       "step": 12000
+    },
+    {
+      "epoch": 1.928,
+      "grad_norm": 6469.14306640625,
+      "learning_rate": 1.072e-05,
+      "loss": 0.0584,
+      "step": 12050
+    },
+    {
+      "epoch": 1.936,
+      "grad_norm": 7579.2998046875,
+      "learning_rate": 1.0640000000000001e-05,
+      "loss": 0.0573,
+      "step": 12100
+    },
+    {
+      "epoch": 1.944,
+      "grad_norm": 8114.94921875,
+      "learning_rate": 1.0559999999999999e-05,
+      "loss": 0.0523,
+      "step": 12150
+    },
+    {
+      "epoch": 1.952,
+      "grad_norm": 7263.44384765625,
+      "learning_rate": 1.048e-05,
+      "loss": 0.0517,
+      "step": 12200
+    },
+    {
+      "epoch": 1.96,
+      "grad_norm": 8325.9580078125,
+      "learning_rate": 1.04e-05,
+      "loss": 0.0524,
+      "step": 12250
+    },
+    {
+      "epoch": 1.968,
+      "grad_norm": 6577.01318359375,
+      "learning_rate": 1.032e-05,
+      "loss": 0.0533,
+      "step": 12300
+    },
+    {
+      "epoch": 1.976,
+      "grad_norm": 6278.1826171875,
+      "learning_rate": 1.024e-05,
+      "loss": 0.0532,
+      "step": 12350
+    },
+    {
+      "epoch": 1.984,
+      "grad_norm": 7769.2333984375,
+      "learning_rate": 1.0160000000000001e-05,
+      "loss": 0.0532,
+      "step": 12400
+    },
+    {
+      "epoch": 1.992,
+      "grad_norm": 10089.91796875,
+      "learning_rate": 1.008e-05,
+      "loss": 0.0539,
+      "step": 12450
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 9177.8115234375,
+      "learning_rate": 9.999999999999999e-06,
+      "loss": 0.0588,
+      "step": 12500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.08158940076828003,
+      "eval_runtime": 116.7903,
+      "eval_samples_per_second": 17.125,
+      "eval_steps_per_second": 2.141,
+      "step": 12500
     }
   ],
   "logging_steps": 50,
@@ -1898,7 +1976,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.845995749376e+16,
+  "total_flos": 6.0895789056e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null