Training in progress, epoch 1, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:359f03565ffde72ca2ba79491c705fe79c6910e9bd98dc4da3c2d72dd984114c
+oid sha256:d64bbbf7ec79e29546cb7d65119bf95bc04ab9c0da747304cf3f474c9aae50b2
 size 2682482800

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9048fafeb2aa676460e8ea091a11b1525206d19f4ef4961093c98af204315634
+oid sha256:86f024ba6223fdab2ac740699aeafb3cafb4c47e8fa408eacd189d78ce45ea86
 size 5365108834

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb357d1fd873b2e9e783702e673b2d6f1de3e1b1f85efe7ccee99b69a6a7abc9
+oid sha256:79a7cc54a48c2d3d9c0c40c558794e33247b93c9b42b8d7aaa243a3e8501a80c
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2fec4fd6bb533b427a0a9db7b7fd25ac543921c09d5d0a518d007b072a567e94
+oid sha256:8de0bc6cfe3797412f398b180e19fce8db21f657cafafd5cdd131c656ee7216d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9979996362975087,
+  "epoch": 1.9979996362975085,
   "eval_steps": 50,
-  "global_step": 343,
+  "global_step": 686,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -97,6 +97,111 @@
       "eval_samples_per_second": 41.367,
       "eval_steps_per_second": 20.683,
       "step": 300
+    },
+    {
+      "epoch": 1.0203673395162758,
+      "grad_norm": 118.28443145751953,
+      "learning_rate": 9.489795918367348e-05,
+      "loss": 1.1973,
+      "step": 350
+    },
+    {
+      "epoch": 1.0203673395162758,
+      "eval_loss": 1.1349806785583496,
+      "eval_runtime": 118.2776,
+      "eval_samples_per_second": 40.802,
+      "eval_steps_per_second": 20.401,
+      "step": 350
+    },
+    {
+      "epoch": 1.165848336061102,
+      "grad_norm": 71.47338104248047,
+      "learning_rate": 9.416909620991254e-05,
+      "loss": 1.159,
+      "step": 400
+    },
+    {
+      "epoch": 1.165848336061102,
+      "eval_loss": 1.1155215501785278,
+      "eval_runtime": 116.539,
+      "eval_samples_per_second": 41.411,
+      "eval_steps_per_second": 20.706,
+      "step": 400
+    },
+    {
+      "epoch": 1.3113293326059283,
+      "grad_norm": 49.708885192871094,
+      "learning_rate": 9.344023323615161e-05,
+      "loss": 1.1471,
+      "step": 450
+    },
+    {
+      "epoch": 1.3113293326059283,
+      "eval_loss": 1.0999969244003296,
+      "eval_runtime": 116.44,
+      "eval_samples_per_second": 41.446,
+      "eval_steps_per_second": 20.723,
+      "step": 450
+    },
+    {
+      "epoch": 1.4568103291507546,
+      "grad_norm": 59.27313995361328,
+      "learning_rate": 9.271137026239067e-05,
+      "loss": 1.1325,
+      "step": 500
+    },
+    {
+      "epoch": 1.4568103291507546,
+      "eval_loss": 1.0860569477081299,
+      "eval_runtime": 116.8329,
+      "eval_samples_per_second": 41.307,
+      "eval_steps_per_second": 20.653,
+      "step": 500
+    },
+    {
+      "epoch": 1.6022913256955809,
+      "grad_norm": 93.8194351196289,
+      "learning_rate": 9.198250728862974e-05,
+      "loss": 1.121,
+      "step": 550
+    },
+    {
+      "epoch": 1.6022913256955809,
+      "eval_loss": 1.0699989795684814,
+      "eval_runtime": 116.3351,
+      "eval_samples_per_second": 41.484,
+      "eval_steps_per_second": 20.742,
+      "step": 550
+    },
+    {
+      "epoch": 1.7477723222404073,
+      "grad_norm": 64.32953643798828,
+      "learning_rate": 9.125364431486881e-05,
+      "loss": 1.1071,
+      "step": 600
+    },
+    {
+      "epoch": 1.7477723222404073,
+      "eval_loss": 1.0575978755950928,
+      "eval_runtime": 116.4201,
+      "eval_samples_per_second": 41.453,
+      "eval_steps_per_second": 20.727,
+      "step": 600
+    },
+    {
+      "epoch": 1.8932533187852338,
+      "grad_norm": 55.454044342041016,
+      "learning_rate": 9.052478134110788e-05,
+      "loss": 1.092,
+      "step": 650
+    },
+    {
+      "epoch": 1.8932533187852338,
+      "eval_loss": 1.0517867803573608,
+      "eval_runtime": 116.5644,
+      "eval_samples_per_second": 41.402,
+      "eval_steps_per_second": 20.701,
+      "step": 650
     }
   ],
   "logging_steps": 50,
@@ -116,7 +221,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.9337717422293e+16,
+  "total_flos": 1.786714457594921e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null