Training in progress, step 3000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a6445366fb72dd64a30a112d0cfda302649ce8c29f7108f12ace64035585c67
+oid sha256:c8050d0ba4cc80419a583c93968e6bf55216baf5e1371c2c9e7133fa0b1464ed
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ebbdc69304c59243d4149daaa710b1485f7a643fa3ccf2294412ebf232abae9
+oid sha256:9b05d6d3a797d87d258d9bcbc672b81e5538c72ed7f79e2144c48b29830d47b1
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca2a334725c06878338083a325b1190cf2f41e51415271d4e791a39c574e91d1
+oid sha256:ee21e9bc6023190a0db96d08050b5e5b20632d2971675b4236e71d6b2aa60903
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3eedbad439d02a3d9e01c697324385512054df489e38825f0e26bf6d99fe88ac
+oid sha256:e4a50e6bc9278ed49513d0c8109e953279561a58261b90ebf3bd479594596325
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.20481644570827484,
-  "best_model_checkpoint": "./fine-tuned/checkpoint-2500",
-  "epoch": 1.7562346329469616,
+  "best_metric": 0.2037852257490158,
+  "best_model_checkpoint": "./fine-tuned/checkpoint-3000",
+  "epoch": 2.107481559536354,
   "eval_steps": 100,
-  "global_step": 2500,
+  "global_step": 3000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -557,6 +557,116 @@
       "eval_samples_per_second": 66.462,
       "eval_steps_per_second": 2.086,
       "step": 2500
+    },
+    {
+      "epoch": 1.7913593256059008,
+      "grad_norm": 20207.35546875,
+      "learning_rate": 1.6560084328882643e-05,
+      "loss": 0.2049,
+      "step": 2550
+    },
+    {
+      "epoch": 1.82648401826484,
+      "grad_norm": 17453.359375,
+      "learning_rate": 1.6296556570625438e-05,
+      "loss": 0.2101,
+      "step": 2600
+    },
+    {
+      "epoch": 1.82648401826484,
+      "eval_loss": 0.20485134422779083,
+      "eval_runtime": 67.202,
+      "eval_samples_per_second": 66.367,
+      "eval_steps_per_second": 2.083,
+      "step": 2600
+    },
+    {
+      "epoch": 1.8616087109237793,
+      "grad_norm": 24568.439453125,
+      "learning_rate": 1.603302881236824e-05,
+      "loss": 0.2081,
+      "step": 2650
+    },
+    {
+      "epoch": 1.8967334035827186,
+      "grad_norm": 22425.1875,
+      "learning_rate": 1.5769501054111034e-05,
+      "loss": 0.2032,
+      "step": 2700
+    },
+    {
+      "epoch": 1.8967334035827186,
+      "eval_loss": 0.2041337788105011,
+      "eval_runtime": 67.2372,
+      "eval_samples_per_second": 66.332,
+      "eval_steps_per_second": 2.082,
+      "step": 2700
+    },
+    {
+      "epoch": 1.9318580962416578,
+      "grad_norm": 21858.3828125,
+      "learning_rate": 1.550597329585383e-05,
+      "loss": 0.2074,
+      "step": 2750
+    },
+    {
+      "epoch": 1.966982788900597,
+      "grad_norm": 17712.39453125,
+      "learning_rate": 1.5242445537596626e-05,
+      "loss": 0.205,
+      "step": 2800
+    },
+    {
+      "epoch": 1.966982788900597,
+      "eval_loss": 0.20371712744235992,
+      "eval_runtime": 67.1299,
+      "eval_samples_per_second": 66.438,
+      "eval_steps_per_second": 2.086,
+      "step": 2800
+    },
+    {
+      "epoch": 2.0021074815595363,
+      "grad_norm": 20413.91796875,
+      "learning_rate": 1.4978917779339424e-05,
+      "loss": 0.203,
+      "step": 2850
+    },
+    {
+      "epoch": 2.0372321742184756,
+      "grad_norm": 21380.130859375,
+      "learning_rate": 1.471539002108222e-05,
+      "loss": 0.199,
+      "step": 2900
+    },
+    {
+      "epoch": 2.0372321742184756,
+      "eval_loss": 0.20416177809238434,
+      "eval_runtime": 67.1771,
+      "eval_samples_per_second": 66.392,
+      "eval_steps_per_second": 2.084,
+      "step": 2900
+    },
+    {
+      "epoch": 2.072356866877415,
+      "grad_norm": 28436.697265625,
+      "learning_rate": 1.4451862262825019e-05,
+      "loss": 0.1989,
+      "step": 2950
+    },
+    {
+      "epoch": 2.107481559536354,
+      "grad_norm": 18739.8359375,
+      "learning_rate": 1.4188334504567815e-05,
+      "loss": 0.1982,
+      "step": 3000
+    },
+    {
+      "epoch": 2.107481559536354,
+      "eval_loss": 0.2037852257490158,
+      "eval_runtime": 67.2417,
+      "eval_samples_per_second": 66.328,
+      "eval_steps_per_second": 2.082,
+      "step": 3000
     }
   ],
   "logging_steps": 50,
@@ -576,7 +686,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.43560320303104e+16,
+  "total_flos": 2.92254115627008e+16,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null