Training in progress, step 157000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd4d2dd6c49affa11f1897287c3a92d51ded625ef3905a93fe2f4fccca4d24fe
+oid sha256:f6fe11c67454b196001e4ed79995fab7a74672309c3dd2962d5f80ffb63bc57b
 size 1410301944

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52d890c69e743122f34fcfde97a19755e7b50f887489442d3dde7487815a67bf
+oid sha256:b377b9ca632415e5cc259fc332790fb52abc8eed12ac83f3e71264ccc731be8f
 size 2820185786

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1b8bd83e18b6a0a16b992311d9cb4c920119703c7f78eac118775c828860191
+oid sha256:a7eb45c212b2ad29aa591c00be2416908d2afe25e585ed34f3beb9e136a92cef
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7335f317de8b0f5ab070f94b9642f4f3cbf0cbf47942933d3d4f3ba522b768a7
+oid sha256:50e7a91a2d6de7899f3ef55596029edda575e3992fc80bcaed05a5c6cf935dee
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.426756581065395,
+  "epoch": 3.4487226393866526,
   "eval_steps": 500,
-  "global_step": 156000,
+  "global_step": 157000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -27776,11 +27776,189 @@
       "eval_steps_per_second": 15.575,
       "num_input_tokens_seen": 90165273280,
       "step": 156000
+    },
+    {
+      "epoch": 3.4278548839814578,
+      "grad_norm": 0.09176173806190491,
+      "learning_rate": 0.0001,
+      "loss": 2.3456,
+      "num_input_tokens_seen": 90217696288,
+      "step": 156050
+    },
+    {
+      "epoch": 3.428953186897521,
+      "grad_norm": 0.089874766767025,
+      "learning_rate": 0.0001,
+      "loss": 2.3475,
+      "num_input_tokens_seen": 90270125088,
+      "step": 156100
+    },
+    {
+      "epoch": 3.4300514898135837,
+      "grad_norm": 0.0928313210606575,
+      "learning_rate": 0.0001,
+      "loss": 2.3515,
+      "num_input_tokens_seen": 90322553888,
+      "step": 156150
+    },
+    {
+      "epoch": 3.4311497927296464,
+      "grad_norm": 0.09114927798509598,
+      "learning_rate": 0.0001,
+      "loss": 2.3494,
+      "num_input_tokens_seen": 90374980192,
+      "step": 156200
+    },
+    {
+      "epoch": 3.4322480956457095,
+      "grad_norm": 0.09503049403429031,
+      "learning_rate": 0.0001,
+      "loss": 2.3439,
+      "num_input_tokens_seen": 90427408992,
+      "step": 156250
+    },
+    {
+      "epoch": 3.4333463985617723,
+      "grad_norm": 0.09301070868968964,
+      "learning_rate": 0.0001,
+      "loss": 2.3487,
+      "num_input_tokens_seen": 90479837120,
+      "step": 156300
+    },
+    {
+      "epoch": 3.434444701477835,
+      "grad_norm": 0.09190023690462112,
+      "learning_rate": 0.0001,
+      "loss": 2.3448,
+      "num_input_tokens_seen": 90532258144,
+      "step": 156350
+    },
+    {
+      "epoch": 3.435543004393898,
+      "grad_norm": 0.09636224061250687,
+      "learning_rate": 0.0001,
+      "loss": 2.3456,
+      "num_input_tokens_seen": 90584686944,
+      "step": 156400
+    },
+    {
+      "epoch": 3.436641307309961,
+      "grad_norm": 0.09875821322202682,
+      "learning_rate": 0.0001,
+      "loss": 2.3415,
+      "num_input_tokens_seen": 90637115744,
+      "step": 156450
+    },
+    {
+      "epoch": 3.437739610226024,
+      "grad_norm": 0.09387224912643433,
+      "learning_rate": 0.0001,
+      "loss": 2.3483,
+      "num_input_tokens_seen": 90689540064,
+      "step": 156500
+    },
+    {
+      "epoch": 3.437739610226024,
+      "eval_loss": 2.2581753730773926,
+      "eval_runtime": 79.6955,
+      "eval_samples_per_second": 62.739,
+      "eval_steps_per_second": 15.685,
+      "num_input_tokens_seen": 90689540064,
+      "step": 156500
+    },
+    {
+      "epoch": 3.4388379131420868,
+      "grad_norm": 0.08944698423147202,
+      "learning_rate": 0.0001,
+      "loss": 2.3459,
+      "num_input_tokens_seen": 90741968864,
+      "step": 156550
+    },
+    {
+      "epoch": 3.4399362160581495,
+      "grad_norm": 0.09725566953420639,
+      "learning_rate": 0.0001,
+      "loss": 2.3399,
+      "num_input_tokens_seen": 90794397664,
+      "step": 156600
+    },
+    {
+      "epoch": 3.4410345189742126,
+      "grad_norm": 0.09932785481214523,
+      "learning_rate": 0.0001,
+      "loss": 2.3475,
+      "num_input_tokens_seen": 90846826464,
+      "step": 156650
+    },
+    {
+      "epoch": 3.4421328218902754,
+      "grad_norm": 0.09854361414909363,
+      "learning_rate": 0.0001,
+      "loss": 2.3449,
+      "num_input_tokens_seen": 90899255264,
+      "step": 156700
+    },
+    {
+      "epoch": 3.4432311248063385,
+      "grad_norm": 0.09402545541524887,
+      "learning_rate": 0.0001,
+      "loss": 2.3434,
+      "num_input_tokens_seen": 90951684064,
+      "step": 156750
+    },
+    {
+      "epoch": 3.4443294277224012,
+      "grad_norm": 0.09715921431779861,
+      "learning_rate": 0.0001,
+      "loss": 2.3455,
+      "num_input_tokens_seen": 91004112864,
+      "step": 156800
+    },
+    {
+      "epoch": 3.445427730638464,
+      "grad_norm": 0.09590257704257965,
+      "learning_rate": 0.0001,
+      "loss": 2.348,
+      "num_input_tokens_seen": 91056541664,
+      "step": 156850
+    },
+    {
+      "epoch": 3.446526033554527,
+      "grad_norm": 0.10155434161424637,
+      "learning_rate": 0.0001,
+      "loss": 2.3403,
+      "num_input_tokens_seen": 91108970464,
+      "step": 156900
+    },
+    {
+      "epoch": 3.44762433647059,
+      "grad_norm": 0.09132086485624313,
+      "learning_rate": 0.0001,
+      "loss": 2.3569,
+      "num_input_tokens_seen": 91161399264,
+      "step": 156950
+    },
+    {
+      "epoch": 3.4487226393866526,
+      "grad_norm": 0.0917491465806961,
+      "learning_rate": 0.0001,
+      "loss": 2.3454,
+      "num_input_tokens_seen": 91213822304,
+      "step": 157000
+    },
+    {
+      "epoch": 3.4487226393866526,
+      "eval_loss": 2.2578930854797363,
+      "eval_runtime": 80.5074,
+      "eval_samples_per_second": 62.106,
+      "eval_steps_per_second": 15.527,
+      "num_input_tokens_seen": 91213822304,
+      "step": 157000
     }
   ],
   "logging_steps": 50,
   "max_steps": 200000,
-  "num_input_tokens_seen": 90165273280,
+  "num_input_tokens_seen": 91213822304,
   "num_train_epochs": 5,
   "save_steps": 1000,
   "stateful_callbacks": {
@@ -27795,7 +27973,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.5957608755975373e+20,
+  "total_flos": 1.614318280768918e+20,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null