Training in progress, step 111000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:280468268c9dc3dc98a5f7a7ce4a8d60a10f5b12520a37769180f2bec1daa16d
+oid sha256:3d918bb0a42fca6cacae9d1bdec880dc5f252219ba38da64e3a58ac700d0c148
 size 1410301944

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ebb5b39fab48f8e10301d7916fa10ee3f2554aff90e9e97c1d6b4360c96a90e5
+oid sha256:a33a3c319d6a66444c7bf9a0b64adb07320f60c802158c31380545be06ce88b0
 size 2820185786

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:854e088763d24e35447d57274113b168aa717fd59556d8b2019a803cfc5a77e8
+oid sha256:d1a86d4ecac3fd0dba06cbaf60a1aa4cb43bd245688d3d1e54473ba75e6bfff0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf2571037dccab0274650d91a33463fc6b544dc2b2d48355d3c687ecaf1ec9e3
+oid sha256:0e6fc7d7e8ba590133db77bb041ad1735fff810d2dc746534b5d880b6609a01e
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.0494079206267812,
+  "epoch": 1.0589479709505467,
   "eval_steps": 500,
-  "global_step": 110000,
+  "global_step": 111000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -19588,11 +19588,189 @@
       "eval_steps_per_second": 15.003,
       "num_input_tokens_seen": 57662439520,
       "step": 110000
+    },
+    {
+      "epoch": 1.0498849231429697,
+      "grad_norm": 0.14630495011806488,
+      "learning_rate": 0.001,
+      "loss": 2.104,
+      "num_input_tokens_seen": 57688651552,
+      "step": 110050
+    },
+    {
+      "epoch": 1.0503619256591579,
+      "grad_norm": 0.15211914479732513,
+      "learning_rate": 0.001,
+      "loss": 2.0929,
+      "num_input_tokens_seen": 57714851968,
+      "step": 110100
+    },
+    {
+      "epoch": 1.050838928175346,
+      "grad_norm": 0.15288826823234558,
+      "learning_rate": 0.001,
+      "loss": 2.107,
+      "num_input_tokens_seen": 57741066368,
+      "step": 110150
+    },
+    {
+      "epoch": 1.0513159306915343,
+      "grad_norm": 0.18201424181461334,
+      "learning_rate": 0.001,
+      "loss": 2.0831,
+      "num_input_tokens_seen": 57767277728,
+      "step": 110200
+    },
+    {
+      "epoch": 1.0517929332077227,
+      "grad_norm": 0.15570518374443054,
+      "learning_rate": 0.001,
+      "loss": 2.1017,
+      "num_input_tokens_seen": 57793489344,
+      "step": 110250
+    },
+    {
+      "epoch": 1.052269935723911,
+      "grad_norm": 0.15590184926986694,
+      "learning_rate": 0.001,
+      "loss": 2.0851,
+      "num_input_tokens_seen": 57819702752,
+      "step": 110300
+    },
+    {
+      "epoch": 1.0527469382400991,
+      "grad_norm": 0.13825973868370056,
+      "learning_rate": 0.001,
+      "loss": 2.0966,
+      "num_input_tokens_seen": 57845893728,
+      "step": 110350
+    },
+    {
+      "epoch": 1.0532239407562876,
+      "grad_norm": 0.1424342691898346,
+      "learning_rate": 0.001,
+      "loss": 2.0915,
+      "num_input_tokens_seen": 57872104704,
+      "step": 110400
+    },
+    {
+      "epoch": 1.0537009432724758,
+      "grad_norm": 0.14073631167411804,
+      "learning_rate": 0.001,
+      "loss": 2.1029,
+      "num_input_tokens_seen": 57898312928,
+      "step": 110450
+    },
+    {
+      "epoch": 1.054177945788664,
+      "grad_norm": 0.1437380015850067,
+      "learning_rate": 0.001,
+      "loss": 2.0945,
+      "num_input_tokens_seen": 57924525696,
+      "step": 110500
+    },
+    {
+      "epoch": 1.054177945788664,
+      "eval_loss": 2.01132869720459,
+      "eval_runtime": 83.1173,
+      "eval_samples_per_second": 60.156,
+      "eval_steps_per_second": 15.039,
+      "num_input_tokens_seen": 57924525696,
+      "step": 110500
+    },
+    {
+      "epoch": 1.0546549483048524,
+      "grad_norm": 0.14192169904708862,
+      "learning_rate": 0.001,
+      "loss": 2.0819,
+      "num_input_tokens_seen": 57950733824,
+      "step": 110550
+    },
+    {
+      "epoch": 1.0551319508210406,
+      "grad_norm": 0.13621965050697327,
+      "learning_rate": 0.001,
+      "loss": 2.096,
+      "num_input_tokens_seen": 57976940256,
+      "step": 110600
+    },
+    {
+      "epoch": 1.0556089533372288,
+      "grad_norm": 0.14394508302211761,
+      "learning_rate": 0.001,
+      "loss": 2.0959,
+      "num_input_tokens_seen": 58003150272,
+      "step": 110650
+    },
+    {
+      "epoch": 1.056085955853417,
+      "grad_norm": 0.15062682330608368,
+      "learning_rate": 0.001,
+      "loss": 2.0912,
+      "num_input_tokens_seen": 58029359264,
+      "step": 110700
+    },
+    {
+      "epoch": 1.0565629583696055,
+      "grad_norm": 0.15145541727542877,
+      "learning_rate": 0.001,
+      "loss": 2.0954,
+      "num_input_tokens_seen": 58055566272,
+      "step": 110750
+    },
+    {
+      "epoch": 1.0570399608857937,
+      "grad_norm": 0.14316266775131226,
+      "learning_rate": 0.001,
+      "loss": 2.0871,
+      "num_input_tokens_seen": 58081774848,
+      "step": 110800
+    },
+    {
+      "epoch": 1.0575169634019819,
+      "grad_norm": 0.1519429087638855,
+      "learning_rate": 0.001,
+      "loss": 2.1033,
+      "num_input_tokens_seen": 58107987648,
+      "step": 110850
+    },
+    {
+      "epoch": 1.0579939659181703,
+      "grad_norm": 0.1556522697210312,
+      "learning_rate": 0.001,
+      "loss": 2.0921,
+      "num_input_tokens_seen": 58134199072,
+      "step": 110900
+    },
+    {
+      "epoch": 1.0584709684343585,
+      "grad_norm": 0.14416266977787018,
+      "learning_rate": 0.001,
+      "loss": 2.0952,
+      "num_input_tokens_seen": 58160410880,
+      "step": 110950
+    },
+    {
+      "epoch": 1.0589479709505467,
+      "grad_norm": 0.14932425320148468,
+      "learning_rate": 0.001,
+      "loss": 2.0978,
+      "num_input_tokens_seen": 58186625280,
+      "step": 111000
+    },
+    {
+      "epoch": 1.0589479709505467,
+      "eval_loss": 2.010718584060669,
+      "eval_runtime": 83.9004,
+      "eval_samples_per_second": 59.594,
+      "eval_steps_per_second": 14.899,
+      "num_input_tokens_seen": 58186625280,
+      "step": 111000
     }
   ],
   "logging_steps": 50,
   "max_steps": 140000,
-  "num_input_tokens_seen": 57662439520,
+  "num_input_tokens_seen": 58186625280,
   "num_train_epochs": 2,
   "save_steps": 1000,
   "stateful_callbacks": {
@@ -19607,7 +19785,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.0205200032143155e+20,
+  "total_flos": 1.0297971350514893e+20,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null