Training in progress, epoch 2, checkpoint

last-checkpoint/adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5452bebc2169d59f486bb3d637b5e2980862268378a18774a4072e2d85251b2c
+oid sha256:5ee5c23e36a220ddfb323d32d463c212f902254630a4ca1f579a0caca6ef359f
 size 2692157

last-checkpoint/global_step1226/mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89cd82ea15fe75736613dff47ec935108aac97520c6feafd3ef6a5ea0a5351ce
+size 1116913857

last-checkpoint/global_step1226/zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8095ed9c2415eed8d4f96ec9276547574c2ed6d8eb4c8997ba3c9f81c07b3dd0
+size 999614

last-checkpoint/global_step1226/zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11e12de0377c60745878d006bd2f73ec378d94085267eab9fa5dd0337029cc22
+size 999614

last-checkpoint/global_step1226/zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc1d9ea8c8e487b2ba85ef9d22488bcde62954d3490969243b167ffc99d54468
+size 999614

last-checkpoint/global_step1226/zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6b7b23671b2745f82bf31c7b80e63063fe9f83368dcfc287a5c270efd8a5f9e
+size 999614

last-checkpoint/global_step1226/zero_pp_rank_4_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adcab907dfac0ac296b9d5e115333d0d0f0b2ad6fb5e95ccdeff755ca8898d5c
+size 999614

last-checkpoint/global_step1226/zero_pp_rank_5_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9269e73f67102ebe55c2515ca8cd91f405f9260c97d298805d292899da3d02f
+size 999614

last-checkpoint/global_step1226/zero_pp_rank_6_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:189a65db859f06ed8939b5f886e49c7c627d4fdccdb8e1d39739abad63c84050
+size 999614

last-checkpoint/global_step1226/zero_pp_rank_7_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b5f06b855b03792c61b5bb65179dfa13de959c1078c89c29503d1956cd5d9e9
+size 999614

last-checkpoint/latest

@@ -1 +1 @@
-global_step613
+global_step1226

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:074fcecc44d29f9d903775b0a4fc073fc9a85a966b7b704aed4489ca81126c0e
+oid sha256:c31e33d70b3fe7f61d71a2b4a5353d94b31f406bedabb2083e35ac5bbc106208
 size 21687

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8545aeda4d84055dca173afd10cd32594b5924773d853968f5554bb6e70ebf5
+oid sha256:38fe384dd20308f07ec5585d9912cb965830bcc11808cbdc846275b932905119
 size 21687

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6a80d655a9645035c7c7291026e2cfd9f8e8eb55b1a8862fc2ff511f21f9637
+oid sha256:39ce95745d8ff40a4f8ee5a97f3689eaa9467213f9b27ce66ca594efc37198cf
 size 21687

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9001ac1081129e2706283300e18bc61db844c3712bcca1053fe46ed27bf5a3d
+oid sha256:c349f517e129599281e2e4a383da6c74c212dfb7e6bad5c542f121cde888a562
 size 21687

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77797acaf94098d48f8dbfbf490d016293ae182de1e3b75a021ea2ad10a3b8c1
+oid sha256:df27a56b73699e712acf3ed2a1bec8b4dc1f7438a81b82196f0c2f34f00b7551
 size 21687

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e3cc6143a6435130c04397fcb9724ee1dfa60a808738b01848904b645df1670
+oid sha256:34696be6d136ea03ea905aa2941fd96da980291d6b92db0de6b0a3b4d6447267
 size 21687

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69d42bd44725be5eeb564d9985403584b6bfc1dc4fca99ffe9d73a5a993e95d1
+oid sha256:f0e2cbda44be671f5b71ae2543f2cec67328a527bccee980bbad52fe0ebf7dd5
 size 21687

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e82bd09a93fcb210c1205df094b3badd3c3b4c7506ea2fe159aa6e17092df73
+oid sha256:4070b9e9beda56664b5815d344e6c0f296840034807befc40392beac83c285b1
 size 21687

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.7203035354614258,
-  "best_model_checkpoint": "outputs/checkpoint-613",
-  "epoch": 1.0,
+  "best_metric": 0.6314801573753357,
+  "best_model_checkpoint": "outputs/checkpoint-1226",
+  "epoch": 2.0,
   "eval_steps": 500,
-  "global_step": 613,
+  "global_step": 1226,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -87,13 +87,93 @@
       "eval_samples_per_second": 568.098,
       "eval_steps_per_second": 17.95,
       "step": 613
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 4.914318573893042e-05,
+      "loss": 0.8284,
+      "step": 650
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 4.8855664174813115e-05,
+      "loss": 0.8152,
+      "step": 700
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 4.856814261069581e-05,
+      "loss": 0.8085,
+      "step": 750
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 4.8280621046578495e-05,
+      "loss": 0.8156,
+      "step": 800
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 4.799309948246118e-05,
+      "loss": 0.7773,
+      "step": 850
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 4.770557791834388e-05,
+      "loss": 0.7913,
+      "step": 900
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 4.741805635422657e-05,
+      "loss": 0.7787,
+      "step": 950
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 4.713053479010926e-05,
+      "loss": 0.7589,
+      "step": 1000
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 4.684301322599195e-05,
+      "loss": 0.7671,
+      "step": 1050
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 4.655549166187464e-05,
+      "loss": 0.7461,
+      "step": 1100
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 4.6267970097757336e-05,
+      "loss": 0.7469,
+      "step": 1150
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 4.598044853364002e-05,
+      "loss": 0.743,
+      "step": 1200
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6314801573753357,
+      "eval_runtime": 2.0735,
+      "eval_samples_per_second": 564.759,
+      "eval_steps_per_second": 17.845,
+      "step": 1226
     }
   ],
   "logging_steps": 50,
   "max_steps": 9195,
   "num_train_epochs": 15,
   "save_steps": 500,
-  "total_flos": 1018911101288448.0,
+  "total_flos": 2038462404362240.0,
   "trial_name": null,
   "trial_params": null
 }