Training in progress, step 32000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99efb4f925ebae40cd6f793929b87a0ccac0e7b97e6def05084db3705337b811
+oid sha256:6f3efdd22645edf9b27968c44325394fb2b759ab91da7c8ce83b3d5624316247
 size 517931840

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aba48d7345e1335acdd811f72ad9602a930b00d7d91d9a11216fc53d7f15cb25
+oid sha256:cdf80f22e7a0541c733f265b4f922632311af4702895a6489cc3c6583b1b00ec
 size 1035661434

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17ffd9dd4a600ef00ffe7371c71cf7eaaf39e90e97468b4a36b4cc557b2fc5d1
+oid sha256:26f742dd126d572747f29fd7ba88348146ec68ecb2ae0d2effd91de53bff9d0d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:277f21680b959b596662b48a96a00aaa486d9a86675c2da90af20e0783552321
+oid sha256:3b45d7a8e84e284c770af40e442ab0efb2fec2b035c2481cdfd246cdf35d0dd1
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6809473405299582,
+  "epoch": 0.7029133837728602,
   "eval_steps": 500,
-  "global_step": 31000,
+  "global_step": 32000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5526,11 +5526,189 @@
       "eval_steps_per_second": 19.005,
       "num_input_tokens_seen": 32505852160,
       "step": 31000
+    },
+    {
+      "epoch": 0.6820456426921033,
+      "grad_norm": 0.143716499209404,
+      "learning_rate": 0.001,
+      "loss": 2.6591,
+      "num_input_tokens_seen": 32558280960,
+      "step": 31050
+    },
+    {
+      "epoch": 0.6831439448542485,
+      "grad_norm": 0.16048283874988556,
+      "learning_rate": 0.001,
+      "loss": 2.659,
+      "num_input_tokens_seen": 32610709760,
+      "step": 31100
+    },
+    {
+      "epoch": 0.6842422470163936,
+      "grad_norm": 0.15203309059143066,
+      "learning_rate": 0.001,
+      "loss": 2.6703,
+      "num_input_tokens_seen": 32663138560,
+      "step": 31150
+    },
+    {
+      "epoch": 0.6853405491785386,
+      "grad_norm": 0.14977113902568817,
+      "learning_rate": 0.001,
+      "loss": 2.6657,
+      "num_input_tokens_seen": 32715567360,
+      "step": 31200
+    },
+    {
+      "epoch": 0.6864388513406837,
+      "grad_norm": 0.15292279422283173,
+      "learning_rate": 0.001,
+      "loss": 2.6629,
+      "num_input_tokens_seen": 32767996160,
+      "step": 31250
+    },
+    {
+      "epoch": 0.6875371535028288,
+      "grad_norm": 0.13721971213817596,
+      "learning_rate": 0.001,
+      "loss": 2.6641,
+      "num_input_tokens_seen": 32820424960,
+      "step": 31300
+    },
+    {
+      "epoch": 0.6886354556649739,
+      "grad_norm": 0.15564891695976257,
+      "learning_rate": 0.001,
+      "loss": 2.6673,
+      "num_input_tokens_seen": 32872853760,
+      "step": 31350
+    },
+    {
+      "epoch": 0.689733757827119,
+      "grad_norm": 0.15267717838287354,
+      "learning_rate": 0.001,
+      "loss": 2.6624,
+      "num_input_tokens_seen": 32925282560,
+      "step": 31400
+    },
+    {
+      "epoch": 0.6908320599892641,
+      "grad_norm": 0.15039384365081787,
+      "learning_rate": 0.001,
+      "loss": 2.6615,
+      "num_input_tokens_seen": 32977711360,
+      "step": 31450
+    },
+    {
+      "epoch": 0.6919303621514092,
+      "grad_norm": 0.14114901423454285,
+      "learning_rate": 0.001,
+      "loss": 2.6663,
+      "num_input_tokens_seen": 33030140160,
+      "step": 31500
+    },
+    {
+      "epoch": 0.6919303621514092,
+      "eval_loss": 2.5618767738342285,
+      "eval_runtime": 66.9611,
+      "eval_samples_per_second": 74.67,
+      "eval_steps_per_second": 18.668,
+      "num_input_tokens_seen": 33030140160,
+      "step": 31500
+    },
+    {
+      "epoch": 0.6930286643135543,
+      "grad_norm": 0.1415725201368332,
+      "learning_rate": 0.001,
+      "loss": 2.6606,
+      "num_input_tokens_seen": 33082568960,
+      "step": 31550
+    },
+    {
+      "epoch": 0.6941269664756994,
+      "grad_norm": 0.14324156939983368,
+      "learning_rate": 0.001,
+      "loss": 2.6616,
+      "num_input_tokens_seen": 33134997760,
+      "step": 31600
+    },
+    {
+      "epoch": 0.6952252686378445,
+      "grad_norm": 0.1544431746006012,
+      "learning_rate": 0.001,
+      "loss": 2.6567,
+      "num_input_tokens_seen": 33187426560,
+      "step": 31650
+    },
+    {
+      "epoch": 0.6963235707999895,
+      "grad_norm": 0.14641186594963074,
+      "learning_rate": 0.001,
+      "loss": 2.6605,
+      "num_input_tokens_seen": 33239855360,
+      "step": 31700
+    },
+    {
+      "epoch": 0.6974218729621346,
+      "grad_norm": 0.13757406175136566,
+      "learning_rate": 0.001,
+      "loss": 2.673,
+      "num_input_tokens_seen": 33292284160,
+      "step": 31750
+    },
+    {
+      "epoch": 0.6985201751242798,
+      "grad_norm": 0.14516425132751465,
+      "learning_rate": 0.001,
+      "loss": 2.6781,
+      "num_input_tokens_seen": 33344712960,
+      "step": 31800
+    },
+    {
+      "epoch": 0.6996184772864249,
+      "grad_norm": 0.15246887505054474,
+      "learning_rate": 0.001,
+      "loss": 2.6683,
+      "num_input_tokens_seen": 33397141760,
+      "step": 31850
+    },
+    {
+      "epoch": 0.7007167794485699,
+      "grad_norm": 0.1413787305355072,
+      "learning_rate": 0.001,
+      "loss": 2.6591,
+      "num_input_tokens_seen": 33449570560,
+      "step": 31900
+    },
+    {
+      "epoch": 0.701815081610715,
+      "grad_norm": 0.16077399253845215,
+      "learning_rate": 0.001,
+      "loss": 2.6628,
+      "num_input_tokens_seen": 33501999360,
+      "step": 31950
+    },
+    {
+      "epoch": 0.7029133837728602,
+      "grad_norm": 0.1555839478969574,
+      "learning_rate": 0.001,
+      "loss": 2.6631,
+      "num_input_tokens_seen": 33554428160,
+      "step": 32000
+    },
+    {
+      "epoch": 0.7029133837728602,
+      "eval_loss": 2.561042547225952,
+      "eval_runtime": 66.7879,
+      "eval_samples_per_second": 74.864,
+      "eval_steps_per_second": 18.716,
+      "num_input_tokens_seen": 33554428160,
+      "step": 32000
     }
   ],
   "logging_steps": 50,
   "max_steps": 200000,
-  "num_input_tokens_seen": 32505852160,
+  "num_input_tokens_seen": 33554428160,
   "num_train_epochs": 5,
   "save_steps": 1000,
   "stateful_callbacks": {
@@ -5545,7 +5723,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.851232100800463e+19,
+  "total_flos": 1.9109492723969556e+19,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null