Training in progress, step 39000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a94fdb7295accdf7201fc02029e5ae45ac44dcd9ef16798d70e0f488636e1f9c
+oid sha256:92d9de77e169ab6755eee5c1e2686926ed90a44667e2ca5eaaa214d0bfb470d0
 size 517931840

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d665c90e6bb04abc526448689a0e7c0f687d8ae7453c9e6c300bb8f38a3b48a2
+oid sha256:32d052133c3436978400ad1196231762f190f602db77149c4cd7cd33bf55ce04
 size 1035661434

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:067fc834db8daa6bcb7d646c19fb2debac62a3ca3a0f0e8b29d38f87eb5e83ea
+oid sha256:25ff3bb999ac5f8f98fec3e5d0ee521c3ada6460eb2706bfa5386f4fa0d04e58
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b9f11080dc8caed5e3c50cfbb46586ae36896ccfee6afab64bede4080bf44b1
+oid sha256:0453f791eed05815dae518781dc172eec5529318c2577a889d73a15d6a871e53
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8347096432302714,
+  "epoch": 0.8566756864731733,
   "eval_steps": 500,
-  "global_step": 38000,
+  "global_step": 39000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6772,11 +6772,189 @@
       "eval_steps_per_second": 18.833,
       "num_input_tokens_seen": 39845884160,
       "step": 38000
+    },
+    {
+      "epoch": 0.8358079453924165,
+      "grad_norm": 0.15346269309520721,
+      "learning_rate": 0.001,
+      "loss": 2.645,
+      "num_input_tokens_seen": 39898312960,
+      "step": 38050
+    },
+    {
+      "epoch": 0.8369062475545616,
+      "grad_norm": 0.1504630148410797,
+      "learning_rate": 0.001,
+      "loss": 2.666,
+      "num_input_tokens_seen": 39950741760,
+      "step": 38100
+    },
+    {
+      "epoch": 0.8380045497167067,
+      "grad_norm": 0.19098903238773346,
+      "learning_rate": 0.001,
+      "loss": 2.6649,
+      "num_input_tokens_seen": 40003170560,
+      "step": 38150
+    },
+    {
+      "epoch": 0.8391028518788518,
+      "grad_norm": 0.15553973615169525,
+      "learning_rate": 0.001,
+      "loss": 2.6565,
+      "num_input_tokens_seen": 40055599360,
+      "step": 38200
+    },
+    {
+      "epoch": 0.8402011540409968,
+      "grad_norm": 0.15650159120559692,
+      "learning_rate": 0.001,
+      "loss": 2.6568,
+      "num_input_tokens_seen": 40108028160,
+      "step": 38250
+    },
+    {
+      "epoch": 0.841299456203142,
+      "grad_norm": 0.17787836492061615,
+      "learning_rate": 0.001,
+      "loss": 2.6497,
+      "num_input_tokens_seen": 40160456960,
+      "step": 38300
+    },
+    {
+      "epoch": 0.8423977583652871,
+      "grad_norm": 0.1535162478685379,
+      "learning_rate": 0.001,
+      "loss": 2.6492,
+      "num_input_tokens_seen": 40212885760,
+      "step": 38350
+    },
+    {
+      "epoch": 0.8434960605274322,
+      "grad_norm": 0.16713359951972961,
+      "learning_rate": 0.001,
+      "loss": 2.6534,
+      "num_input_tokens_seen": 40265314560,
+      "step": 38400
+    },
+    {
+      "epoch": 0.8445943626895772,
+      "grad_norm": 0.17087998986244202,
+      "learning_rate": 0.001,
+      "loss": 2.6602,
+      "num_input_tokens_seen": 40317743360,
+      "step": 38450
+    },
+    {
+      "epoch": 0.8456926648517223,
+      "grad_norm": 0.15651412308216095,
+      "learning_rate": 0.001,
+      "loss": 2.6547,
+      "num_input_tokens_seen": 40370172160,
+      "step": 38500
+    },
+    {
+      "epoch": 0.8456926648517223,
+      "eval_loss": 2.5524706840515137,
+      "eval_runtime": 66.5023,
+      "eval_samples_per_second": 75.185,
+      "eval_steps_per_second": 18.796,
+      "num_input_tokens_seen": 40370172160,
+      "step": 38500
+    },
+    {
+      "epoch": 0.8467909670138675,
+      "grad_norm": 0.15205898880958557,
+      "learning_rate": 0.001,
+      "loss": 2.6541,
+      "num_input_tokens_seen": 40422600960,
+      "step": 38550
+    },
+    {
+      "epoch": 0.8478892691760125,
+      "grad_norm": 0.15865832567214966,
+      "learning_rate": 0.001,
+      "loss": 2.6536,
+      "num_input_tokens_seen": 40475029760,
+      "step": 38600
+    },
+    {
+      "epoch": 0.8489875713381576,
+      "grad_norm": 0.133284330368042,
+      "learning_rate": 0.001,
+      "loss": 2.6531,
+      "num_input_tokens_seen": 40527458560,
+      "step": 38650
+    },
+    {
+      "epoch": 0.8500858735003027,
+      "grad_norm": 0.1421806663274765,
+      "learning_rate": 0.001,
+      "loss": 2.6558,
+      "num_input_tokens_seen": 40579887360,
+      "step": 38700
+    },
+    {
+      "epoch": 0.8511841756624479,
+      "grad_norm": 0.19429996609687805,
+      "learning_rate": 0.001,
+      "loss": 2.6628,
+      "num_input_tokens_seen": 40632316160,
+      "step": 38750
+    },
+    {
+      "epoch": 0.8522824778245929,
+      "grad_norm": 0.14661937952041626,
+      "learning_rate": 0.001,
+      "loss": 2.6594,
+      "num_input_tokens_seen": 40684744960,
+      "step": 38800
+    },
+    {
+      "epoch": 0.853380779986738,
+      "grad_norm": 0.1694687008857727,
+      "learning_rate": 0.001,
+      "loss": 2.6571,
+      "num_input_tokens_seen": 40737173760,
+      "step": 38850
+    },
+    {
+      "epoch": 0.8544790821488831,
+      "grad_norm": 0.152188241481781,
+      "learning_rate": 0.001,
+      "loss": 2.6534,
+      "num_input_tokens_seen": 40789602560,
+      "step": 38900
+    },
+    {
+      "epoch": 0.8555773843110281,
+      "grad_norm": 0.1554640680551529,
+      "learning_rate": 0.001,
+      "loss": 2.649,
+      "num_input_tokens_seen": 40842031360,
+      "step": 38950
+    },
+    {
+      "epoch": 0.8566756864731733,
+      "grad_norm": 0.1481955647468567,
+      "learning_rate": 0.001,
+      "loss": 2.6527,
+      "num_input_tokens_seen": 40894460160,
+      "step": 39000
+    },
+    {
+      "epoch": 0.8566756864731733,
+      "eval_loss": 2.547664165496826,
+      "eval_runtime": 66.2874,
+      "eval_samples_per_second": 75.429,
+      "eval_steps_per_second": 18.857,
+      "num_input_tokens_seen": 40894460160,
+      "step": 39000
     }
   ],
   "logging_steps": 50,
   "max_steps": 200000,
-  "num_input_tokens_seen": 39845884160,
+  "num_input_tokens_seen": 40894460160,
   "num_train_epochs": 5,
   "save_steps": 1000,
   "stateful_callbacks": {
@@ -6791,7 +6969,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.2692523019759124e+19,
+  "total_flos": 2.3289694735724052e+19,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null