Training in progress, step 125000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6da59dcdd189ba50995bfaca6dfb3c1f07cec1d39f2b04e6b589b61aa33bf008
+oid sha256:811ff470374af97e47c736f298958834b69f1700c42f81f0e13b4a5264484ae8
 size 1410301944

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0a4aebfce2ae0e56c21f66beb3519294df5637c5928eb84133802b9a02f01ec
+oid sha256:6d11d76e5f8cf7c010d7ddfa9e036517a28b9f13eec8d65dc499e46a38c1f4b3
 size 2820185786

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98f0ee0fd151b13dc8525e6639746bb04660a2a355f86970459a4f08c593ef0a
+oid sha256:bc320281dd48fee58a87ebe65c5af2ea4c357e61810ad0f123ab838f0f93b01f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4c196ff888110afc03a5fac8e049987b043db46c6b51b50b9a63aa8569f2b7f
+oid sha256:31f9a4be764158103ef48222bfd8b15ec527d59f5ba7b3fa5af00980fe9404f9
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.1829686251594977,
+  "epoch": 1.1925086754832632,
   "eval_steps": 500,
-  "global_step": 124000,
+  "global_step": 125000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -22080,11 +22080,189 @@
       "eval_steps_per_second": 15.101,
       "num_input_tokens_seen": 65001257824,
       "step": 124000
+    },
+    {
+      "epoch": 1.183445627675686,
+      "grad_norm": 0.12966303527355194,
+      "learning_rate": 0.0006085240641360281,
+      "loss": 2.0655,
+      "num_input_tokens_seen": 65027466432,
+      "step": 124050
+    },
+    {
+      "epoch": 1.1839226301918742,
+      "grad_norm": 0.13216206431388855,
+      "learning_rate": 0.0006057842458386314,
+      "loss": 2.0787,
+      "num_input_tokens_seen": 65053680192,
+      "step": 124100
+    },
+    {
+      "epoch": 1.1843996327080626,
+      "grad_norm": 0.13295891880989075,
+      "learning_rate": 0.0006030410983131733,
+      "loss": 2.0654,
+      "num_input_tokens_seen": 65079892928,
+      "step": 124150
+    },
+    {
+      "epoch": 1.1848766352242508,
+      "grad_norm": 0.14478819072246552,
+      "learning_rate": 0.0006002947078916364,
+      "loss": 2.0638,
+      "num_input_tokens_seen": 65106107328,
+      "step": 124200
+    },
+    {
+      "epoch": 1.185353637740439,
+      "grad_norm": 0.13410045206546783,
+      "learning_rate": 0.0005975451610080642,
+      "loss": 2.0711,
+      "num_input_tokens_seen": 65132321728,
+      "step": 124250
+    },
+    {
+      "epoch": 1.1858306402566274,
+      "grad_norm": 0.14699777960777283,
+      "learning_rate": 0.0005947925441958392,
+      "loss": 2.0574,
+      "num_input_tokens_seen": 65158534656,
+      "step": 124300
+    },
+    {
+      "epoch": 1.1863076427728156,
+      "grad_norm": 0.13368327915668488,
+      "learning_rate": 0.0005920369440849609,
+      "loss": 2.0626,
+      "num_input_tokens_seen": 65184748736,
+      "step": 124350
+    },
+    {
+      "epoch": 1.1867846452890038,
+      "grad_norm": 0.13047395646572113,
+      "learning_rate": 0.0005892784473993184,
+      "loss": 2.06,
+      "num_input_tokens_seen": 65210950912,
+      "step": 124400
+    },
+    {
+      "epoch": 1.187261647805192,
+      "grad_norm": 0.13072432577610016,
+      "learning_rate": 0.0005865171409539613,
+      "loss": 2.0869,
+      "num_input_tokens_seen": 65237165312,
+      "step": 124450
+    },
+    {
+      "epoch": 1.1877386503213805,
+      "grad_norm": 0.14443765580654144,
+      "learning_rate": 0.0005837531116523682,
+      "loss": 2.0675,
+      "num_input_tokens_seen": 65263378112,
+      "step": 124500
+    },
+    {
+      "epoch": 1.1877386503213805,
+      "eval_loss": 1.9832085371017456,
+      "eval_runtime": 83.5278,
+      "eval_samples_per_second": 59.86,
+      "eval_steps_per_second": 14.965,
+      "num_input_tokens_seen": 65263378112,
+      "step": 124500
+    },
+    {
+      "epoch": 1.1882156528375687,
+      "grad_norm": 0.13271184265613556,
+      "learning_rate": 0.0005809864464837105,
+      "loss": 2.0507,
+      "num_input_tokens_seen": 65289588448,
+      "step": 124550
+    },
+    {
+      "epoch": 1.188692655353757,
+      "grad_norm": 0.13720299303531647,
+      "learning_rate": 0.0005782172325201155,
+      "loss": 2.0728,
+      "num_input_tokens_seen": 65315802432,
+      "step": 124600
+    },
+    {
+      "epoch": 1.1891696578699453,
+      "grad_norm": 0.12747812271118164,
+      "learning_rate": 0.0005754455569139257,
+      "loss": 2.0786,
+      "num_input_tokens_seen": 65342011648,
+      "step": 124650
+    },
+    {
+      "epoch": 1.1896466603861335,
+      "grad_norm": 0.13649390637874603,
+      "learning_rate": 0.0005726715068949564,
+      "loss": 2.0578,
+      "num_input_tokens_seen": 65368225184,
+      "step": 124700
+    },
+    {
+      "epoch": 1.1901236629023217,
+      "grad_norm": 0.13283640146255493,
+      "learning_rate": 0.0005698951697677498,
+      "loss": 2.0616,
+      "num_input_tokens_seen": 65394434464,
+      "step": 124750
+    },
+    {
+      "epoch": 1.1906006654185102,
+      "grad_norm": 0.13304251432418823,
+      "learning_rate": 0.0005671166329088278,
+      "loss": 2.0657,
+      "num_input_tokens_seen": 65420648864,
+      "step": 124800
+    },
+    {
+      "epoch": 1.1910776679346984,
+      "grad_norm": 0.1442023664712906,
+      "learning_rate": 0.000564335983763942,
+      "loss": 2.0584,
+      "num_input_tokens_seen": 65446854944,
+      "step": 124850
+    },
+    {
+      "epoch": 1.1915546704508866,
+      "grad_norm": 0.13637055456638336,
+      "learning_rate": 0.0005615533098453215,
+      "loss": 2.0719,
+      "num_input_tokens_seen": 65473067296,
+      "step": 124900
+    },
+    {
+      "epoch": 1.192031672967075,
+      "grad_norm": 0.13165481388568878,
+      "learning_rate": 0.0005587686987289189,
+      "loss": 2.0594,
+      "num_input_tokens_seen": 65499281184,
+      "step": 124950
+    },
+    {
+      "epoch": 1.1925086754832632,
+      "grad_norm": 0.14200669527053833,
+      "learning_rate": 0.0005559822380516539,
+      "loss": 2.0692,
+      "num_input_tokens_seen": 65525493280,
+      "step": 125000
+    },
+    {
+      "epoch": 1.1925086754832632,
+      "eval_loss": 1.982203722000122,
+      "eval_runtime": 82.3332,
+      "eval_samples_per_second": 60.729,
+      "eval_steps_per_second": 15.182,
+      "num_input_tokens_seen": 65525493280,
+      "step": 125000
     }
   ],
   "logging_steps": 50,
   "max_steps": 140000,
-  "num_input_tokens_seen": 65001257824,
+  "num_input_tokens_seen": 65525493280,
   "num_train_epochs": 2,
   "save_steps": 1000,
   "stateful_callbacks": {
@@ -22099,7 +22277,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.150403701190529e+20,
+  "total_flos": 1.1596817125562573e+20,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null