Training in progress, step 7500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a082886572e13067532489a5fc1dcb98c513570df4676ae62b39ded1c25bb7e4
+oid sha256:95b216ca2f0f331cd0fb1b5060aae7303e018fd811a626e11c3f50b85f075124
 size 441688704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72a510a1be1e74db7c7d7a99d3f3d239298e6879c992b42b0e0f01ea7eacdb9b
+oid sha256:730fa392e5f88931f6f53528627829ab93c230c150c53ca715559afeb980893d
 size 883473803

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a3c0e5c96be49e3d0f56967ef3a66294b8033a429d896ba1c57076548eb65a4
+oid sha256:9ccaae7b7094e3f6ae09519a1d8593eea1044e5a091df08ba92284c2a368db5a
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a68ceae7165f4c88c8c4809f6ef958049408efc4229565cd13a1f7800728538
+oid sha256:67e9e63342c9fc618c8284b5217646e8560302dc68c6c23a6c0fc311b7d330bf
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d119247b2cee9414eefc7d0552fb04c1f86b7b19685ed262e23f9b9c7cf23594
+oid sha256:e6847feb481bac2207bbdccaefe424c80456cc08ed8d62eb651573dfcd4ddaea
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8235294117647058,
+  "epoch": 0.8823529411764706,
   "eval_steps": 500,
-  "global_step": 7000,
+  "global_step": 7500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1100,6 +1100,84 @@
       "eval_samples_per_second": 49.195,
       "eval_steps_per_second": 1.539,
       "step": 7000
+    },
+    {
+      "epoch": 0.8294117647058824,
+      "grad_norm": 0.37701481580734253,
+      "learning_rate": 8.535294117647059e-05,
+      "loss": 3.5055966186523437,
+      "step": 7050
+    },
+    {
+      "epoch": 0.8352941176470589,
+      "grad_norm": 0.4007062017917633,
+      "learning_rate": 8.241176470588235e-05,
+      "loss": 3.533425598144531,
+      "step": 7100
+    },
+    {
+      "epoch": 0.8411764705882353,
+      "grad_norm": 0.3913261294364929,
+      "learning_rate": 7.947058823529412e-05,
+      "loss": 3.515142822265625,
+      "step": 7150
+    },
+    {
+      "epoch": 0.8470588235294118,
+      "grad_norm": 0.38521477580070496,
+      "learning_rate": 7.65294117647059e-05,
+      "loss": 3.5471871948242186,
+      "step": 7200
+    },
+    {
+      "epoch": 0.8529411764705882,
+      "grad_norm": 0.35928088426589966,
+      "learning_rate": 7.358823529411765e-05,
+      "loss": 3.512651062011719,
+      "step": 7250
+    },
+    {
+      "epoch": 0.8588235294117647,
+      "grad_norm": 0.37140655517578125,
+      "learning_rate": 7.064705882352941e-05,
+      "loss": 3.5302188110351564,
+      "step": 7300
+    },
+    {
+      "epoch": 0.8647058823529412,
+      "grad_norm": 0.36203840374946594,
+      "learning_rate": 6.770588235294118e-05,
+      "loss": 3.5184359741210938,
+      "step": 7350
+    },
+    {
+      "epoch": 0.8705882352941177,
+      "grad_norm": 0.35999393463134766,
+      "learning_rate": 6.476470588235295e-05,
+      "loss": 3.506470031738281,
+      "step": 7400
+    },
+    {
+      "epoch": 0.8764705882352941,
+      "grad_norm": 0.3602432608604431,
+      "learning_rate": 6.18235294117647e-05,
+      "loss": 3.4295809936523436,
+      "step": 7450
+    },
+    {
+      "epoch": 0.8823529411764706,
+      "grad_norm": 0.3545781075954437,
+      "learning_rate": 5.888235294117647e-05,
+      "loss": 3.2766519165039063,
+      "step": 7500
+    },
+    {
+      "epoch": 0.8823529411764706,
+      "eval_loss": 3.3576905727386475,
+      "eval_runtime": 175.7349,
+      "eval_samples_per_second": 49.467,
+      "eval_steps_per_second": 1.548,
+      "step": 7500
     }
   ],
   "logging_steps": 50,
@@ -1119,7 +1197,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.17058830336e+17,
+  "total_flos": 1.2542017536e+17,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null