Training in progress, step 132000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18f6247fa697227171786e92b63492b81203ba9ab620eea2a35269c2dc5abc91
+oid sha256:d9e57d7de320997016d5d2199393f3c6d5ccbb8649da9e46ae713874cd8a8e24
 size 1410301944

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a79b728b1351b728e46db09ab4e3bda84220fcf605f8e84a1af65a7e98ccf401
+oid sha256:6f36f287a4da99bdaf6e0deca55af9eddec679234fd5785a93d74c5b7275a731
 size 2820185786

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13afedcbea29e4911157dfdebca89adaca3015ec55fbe8952619bfb77f49f98b
+oid sha256:3da6ad8ffd940afd42f47dbccd6a99fedee37b4e239b9c682223ad1635ee1326
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d530307a60624b67b44a38452390579f46394dc6c46c3e7e0b33446906fdcfb9
+oid sha256:21aed170a2d0b5ca9750f891383cff878afad1161fd25ef679259c6d8c42258b
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.249748977425856,
+  "epoch": 1.2592890277496214,
   "eval_steps": 500,
-  "global_step": 131000,
+  "global_step": 132000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -23326,11 +23326,189 @@
       "eval_steps_per_second": 15.164,
       "num_input_tokens_seen": 68670633664,
       "step": 131000
+    },
+    {
+      "epoch": 1.2502259799420443,
+      "grad_norm": 0.13041457533836365,
+      "learning_rate": 0.000231613104386454,
+      "loss": 2.0362,
+      "num_input_tokens_seen": 68696842016,
+      "step": 131050
+    },
+    {
+      "epoch": 1.2507029824582325,
+      "grad_norm": 0.1306309849023819,
+      "learning_rate": 0.00022925069366813716,
+      "loss": 2.0593,
+      "num_input_tokens_seen": 68723054176,
+      "step": 131100
+    },
+    {
+      "epoch": 1.2511799849744207,
+      "grad_norm": 0.12761172652244568,
+      "learning_rate": 0.00022689680393686457,
+      "loss": 2.0496,
+      "num_input_tokens_seen": 68749263552,
+      "step": 131150
+    },
+    {
+      "epoch": 1.251656987490609,
+      "grad_norm": 0.12187056988477707,
+      "learning_rate": 0.0002245515092739488,
+      "loss": 2.0417,
+      "num_input_tokens_seen": 68775477952,
+      "step": 131200
+    },
+    {
+      "epoch": 1.2521339900067971,
+      "grad_norm": 0.12770666182041168,
+      "learning_rate": 0.00022221488349019903,
+      "loss": 2.0332,
+      "num_input_tokens_seen": 68801692352,
+      "step": 131250
+    },
+    {
+      "epoch": 1.2526109925229856,
+      "grad_norm": 0.13457396626472473,
+      "learning_rate": 0.00021988700012359863,
+      "loss": 2.0393,
+      "num_input_tokens_seen": 68827900832,
+      "step": 131300
+    },
+    {
+      "epoch": 1.2530879950391738,
+      "grad_norm": 0.12845295667648315,
+      "learning_rate": 0.0002175679324369913,
+      "loss": 2.0507,
+      "num_input_tokens_seen": 68854107328,
+      "step": 131350
+    },
+    {
+      "epoch": 1.2535649975553622,
+      "grad_norm": 0.12990029156208038,
+      "learning_rate": 0.00021525775341577403,
+      "loss": 2.0373,
+      "num_input_tokens_seen": 68880316256,
+      "step": 131400
+    },
+    {
+      "epoch": 1.2540420000715504,
+      "grad_norm": 0.12344187498092651,
+      "learning_rate": 0.00021295653576560165,
+      "loss": 2.0359,
+      "num_input_tokens_seen": 68906521376,
+      "step": 131450
+    },
+    {
+      "epoch": 1.2545190025877386,
+      "grad_norm": 0.12487955391407013,
+      "learning_rate": 0.00021066435191009715,
+      "loss": 2.0432,
+      "num_input_tokens_seen": 68932735776,
+      "step": 131500
+    },
+    {
+      "epoch": 1.2545190025877386,
+      "eval_loss": 1.9613933563232422,
+      "eval_runtime": 82.9225,
+      "eval_samples_per_second": 60.297,
+      "eval_steps_per_second": 15.074,
+      "num_input_tokens_seen": 68932735776,
+      "step": 131500
+    },
+    {
+      "epoch": 1.2549960051039268,
+      "grad_norm": 0.13224980235099792,
+      "learning_rate": 0.00020838127398857382,
+      "loss": 2.0413,
+      "num_input_tokens_seen": 68958946656,
+      "step": 131550
+    },
+    {
+      "epoch": 1.2554730076201153,
+      "grad_norm": 0.12449366599321365,
+      "learning_rate": 0.00020610737385376348,
+      "loss": 2.0503,
+      "num_input_tokens_seen": 68985155520,
+      "step": 131600
+    },
+    {
+      "epoch": 1.2559500101363035,
+      "grad_norm": 0.12943805754184723,
+      "learning_rate": 0.0002038427230695565,
+      "loss": 2.0476,
+      "num_input_tokens_seen": 69011368384,
+      "step": 131650
+    },
+    {
+      "epoch": 1.2564270126524917,
+      "grad_norm": 0.1288331300020218,
+      "learning_rate": 0.00020158739290874821,
+      "loss": 2.0458,
+      "num_input_tokens_seen": 69037580736,
+      "step": 131700
+    },
+    {
+      "epoch": 1.25690401516868,
+      "grad_norm": 0.12655895948410034,
+      "learning_rate": 0.00019934145435079704,
+      "loss": 2.0474,
+      "num_input_tokens_seen": 69063793760,
+      "step": 131750
+    },
+    {
+      "epoch": 1.2573810176848683,
+      "grad_norm": 0.1263783723115921,
+      "learning_rate": 0.0001971049780795901,
+      "loss": 2.0387,
+      "num_input_tokens_seen": 69090002496,
+      "step": 131800
+    },
+    {
+      "epoch": 1.2578580202010565,
+      "grad_norm": 0.13202515244483948,
+      "learning_rate": 0.0001948780344812181,
+      "loss": 2.0531,
+      "num_input_tokens_seen": 69116216896,
+      "step": 131850
+    },
+    {
+      "epoch": 1.2583350227172447,
+      "grad_norm": 0.12061940133571625,
+      "learning_rate": 0.00019266069364176142,
+      "loss": 2.052,
+      "num_input_tokens_seen": 69142427680,
+      "step": 131900
+    },
+    {
+      "epoch": 1.2588120252334332,
+      "grad_norm": 0.1222308874130249,
+      "learning_rate": 0.00019045302534508295,
+      "loss": 2.0409,
+      "num_input_tokens_seen": 69168631136,
+      "step": 131950
+    },
+    {
+      "epoch": 1.2592890277496214,
+      "grad_norm": 0.11664976924657822,
+      "learning_rate": 0.00018825509907063325,
+      "loss": 2.0361,
+      "num_input_tokens_seen": 69194840608,
+      "step": 132000
+    },
+    {
+      "epoch": 1.2592890277496214,
+      "eval_loss": 1.9602855443954468,
+      "eval_runtime": 82.6066,
+      "eval_samples_per_second": 60.528,
+      "eval_steps_per_second": 15.132,
+      "num_input_tokens_seen": 69194840608,
+      "step": 132000
     }
   ],
   "logging_steps": 50,
   "max_steps": 140000,
-  "num_input_tokens_seen": 68670633664,
+  "num_input_tokens_seen": 69194840608,
   "num_train_epochs": 2,
   "save_steps": 1000,
   "stateful_callbacks": {
@@ -23345,7 +23523,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.2153449606169969e+20,
+  "total_flos": 1.224622467372331e+20,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null