Training in progress, step 900, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b60bd2b618a69841c9638940c605adda6c4341ba295b93f3a6e133859850d9b
+oid sha256:dddca729ab09142c6d4a86292fcb09c8240e120212ff2dea7784702f1c454342
 size 579748776

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f82169ccf1b0127e9b22314f600b128025f5b62090d5a9708b8fcba2a47577d6
+oid sha256:b9ae4821caa875af2772c8c1c8a8f25674e533cf460c88cc3b72e2ecf795355b
 size 1159627083

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b88b1c42229400fab90420f6e5c036d698ae72e0815465d44c9b14b967936d62
+oid sha256:5387f6e99d51202c7ef90fef723e457487d08949715af1e6a0aff706c078f5bd
 size 14917

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a24f1bcbda0bf3e5430414e8c982c53ac11d90f165724ef0b93f5942d606b3a0
+oid sha256:a6418bc04f5e424107d7c94f43f8158a47397e1e0f7c2b0b675aeed07c6fcfe3
 size 14917

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4be5aafe091abf14e9046be44e4c580810411461427a26c13cdf5ca05ae54bc2
+oid sha256:4fdb738e61f6acc5e69da32f32a665c3f109e78a2b1b3b8004b382d7b5d9fa18
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3,
+  "epoch": 0.45,
   "eval_steps": 100,
-  "global_step": 600,
+  "global_step": 900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -230,6 +230,117 @@
       "eval_samples_per_second": 63.619,
       "eval_steps_per_second": 2.099,
       "step": 600
+    },
+    {
+      "epoch": 0.3125,
+      "grad_norm": 20.58213233947754,
+      "learning_rate": 8.465819331784009e-05,
+      "loss": 96.2906,
+      "step": 625
+    },
+    {
+      "epoch": 0.325,
+      "grad_norm": 14.315438270568848,
+      "learning_rate": 8.30974265247088e-05,
+      "loss": 95.9487,
+      "step": 650
+    },
+    {
+      "epoch": 0.3375,
+      "grad_norm": 12.04114818572998,
+      "learning_rate": 8.147701593190385e-05,
+      "loss": 95.4309,
+      "step": 675
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 22.478317260742188,
+      "learning_rate": 7.979988162883804e-05,
+      "loss": 95.0101,
+      "step": 700
+    },
+    {
+      "epoch": 0.35,
+      "eval_accuracy": 0.16826703154110645,
+      "eval_loss": 5.88900899887085,
+      "eval_runtime": 7.5208,
+      "eval_samples_per_second": 64.487,
+      "eval_steps_per_second": 2.127,
+      "step": 700
+    },
+    {
+      "epoch": 0.3625,
+      "grad_norm": 50.81674575805664,
+      "learning_rate": 7.806904592488408e-05,
+      "loss": 94.8858,
+      "step": 725
+    },
+    {
+      "epoch": 0.375,
+      "grad_norm": 20.65149688720703,
+      "learning_rate": 7.628762790296879e-05,
+      "loss": 95.0119,
+      "step": 750
+    },
+    {
+      "epoch": 0.3875,
+      "grad_norm": 22.1734619140625,
+      "learning_rate": 7.445883779877482e-05,
+      "loss": 94.6604,
+      "step": 775
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 20.18880844116211,
+      "learning_rate": 7.258597121567904e-05,
+      "loss": 94.2643,
+      "step": 800
+    },
+    {
+      "epoch": 0.4,
+      "eval_accuracy": 0.17154484269838785,
+      "eval_loss": 5.828437328338623,
+      "eval_runtime": 7.4208,
+      "eval_samples_per_second": 65.357,
+      "eval_steps_per_second": 2.156,
+      "step": 800
+    },
+    {
+      "epoch": 0.4125,
+      "grad_norm": 35.1305046081543,
+      "learning_rate": 7.067240318585242e-05,
+      "loss": 94.3216,
+      "step": 825
+    },
+    {
+      "epoch": 0.425,
+      "grad_norm": 9.143704414367676,
+      "learning_rate": 6.872158208822398e-05,
+      "loss": 93.9239,
+      "step": 850
+    },
+    {
+      "epoch": 0.4375,
+      "grad_norm": 9.495540618896484,
+      "learning_rate": 6.673702343426894e-05,
+      "loss": 93.8027,
+      "step": 875
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 19.112733840942383,
+      "learning_rate": 6.472230353281925e-05,
+      "loss": 93.2266,
+      "step": 900
+    },
+    {
+      "epoch": 0.45,
+      "eval_accuracy": 0.17456010582705153,
+      "eval_loss": 5.77442741394043,
+      "eval_runtime": 7.4706,
+      "eval_samples_per_second": 64.921,
+      "eval_steps_per_second": 2.142,
+      "step": 900
     }
   ],
   "logging_steps": 25,
@@ -249,7 +360,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.013344142917632e+17,
+  "total_flos": 6.020016214376448e+17,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null