Upload 38 files

adapter_config.json

@@ -0,0 +1,16 @@
+{
+  "base_model_name_or_path": "togethercomputer/RedPajama-INCITE-Chat-7B-v0.1",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "target_modules": [
+    "query_key_value"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e43bd7d0f57c0c2fbf9d004bbe2fd47f147798e6dc8df8e3f1cad0a98f8245f
+size 16800753

checkpoint-200/adapter_model/adapter_config.json

@@ -0,0 +1,16 @@
+{
+  "base_model_name_or_path": "togethercomputer/RedPajama-INCITE-Chat-7B-v0.1",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "target_modules": [
+    "query_key_value"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-200/adapter_model/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f09b05a44f104d0293c8033ae188364129e985bf4adae5b4112a41d3a7d28eab
+size 16800753

checkpoint-200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbdede2a747d6f3cb3e20b89d078e9f9daf20eaf4cd40ccdaaa5df8813ad023e
+size 33608197

checkpoint-200/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:961839e0107bc944e36119074486d9de18f51c0b49d10582a1f9d9f6a0f7283b
+size 18679

checkpoint-200/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc65543a168d02aa44199021854e49b7f63b51709d1c4cdd4253603bdabc0dac
+size 18679

checkpoint-200/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d277aa58101d8b456e452c3fee973c92f5598876119abfbe9f374a76cd745eac
+size 18679

checkpoint-200/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:898646c2f3a5e6a9ff832f75526439fc16041f63e4108bcca1b4381557beac1f
+size 18679

checkpoint-200/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5133bde2276c6423d4642da8b0dd9e122eca208c10e61053f019b7f2fa8b40
+size 18679

checkpoint-200/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fccf0f9be1bb8f24861e4393745b3e09cc2687125a69e3757955fb0f0925ea5
+size 557

checkpoint-200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:541dca843bbd76c64cb97c112d657f071d35e254ae28f1849b22358f3024b6fb
+size 627

checkpoint-200/trainer_state.json

@@ -0,0 +1,144 @@
+{
+  "best_metric": 2.0006659030914307,
+  "best_model_checkpoint": "./lora-redpajama/checkpoint-200",
+  "epoch": 0.9153318077803204,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05,
+      "learning_rate": 2.9999999999999997e-05,
+      "loss": 5.6682,
+      "step": 10
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 5.9999999999999995e-05,
+      "loss": 5.1317,
+      "step": 20
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 8.999999999999999e-05,
+      "loss": 4.1627,
+      "step": 30
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00011999999999999999,
+      "loss": 3.1593,
+      "step": 40
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00015,
+      "loss": 2.6813,
+      "step": 50
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00017999999999999998,
+      "loss": 2.4024,
+      "step": 60
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00020999999999999998,
+      "loss": 2.3087,
+      "step": 70
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00023999999999999998,
+      "loss": 2.2026,
+      "step": 80
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00027,
+      "loss": 2.1257,
+      "step": 90
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003,
+      "loss": 2.118,
+      "step": 100
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0002945848375451263,
+      "loss": 2.076,
+      "step": 110
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00028916967509025267,
+      "loss": 2.0684,
+      "step": 120
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.000283754512635379,
+      "loss": 2.0212,
+      "step": 130
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.00027833935018050537,
+      "loss": 2.0192,
+      "step": 140
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00027292418772563177,
+      "loss": 1.9991,
+      "step": 150
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0002675090252707581,
+      "loss": 2.0075,
+      "step": 160
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00026209386281588447,
+      "loss": 2.0414,
+      "step": 170
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0002566787003610108,
+      "loss": 2.0048,
+      "step": 180
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.00025126353790613716,
+      "loss": 1.9604,
+      "step": 190
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.0002458483754512635,
+      "loss": 1.9739,
+      "step": 200
+    },
+    {
+      "epoch": 0.92,
+      "eval_loss": 2.0006659030914307,
+      "eval_runtime": 83.0225,
+      "eval_samples_per_second": 24.09,
+      "eval_steps_per_second": 0.602,
+      "step": 200
+    }
+  ],
+  "max_steps": 654,
+  "num_train_epochs": 3,
+  "total_flos": 2.0791481950273536e+17,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e536f96c30f2c2d7847620d7ea3b09863677cb114362f51ccee9bbaba571a29
+size 3963

checkpoint-400/adapter_model/adapter_config.json

@@ -0,0 +1,16 @@
+{
+  "base_model_name_or_path": "togethercomputer/RedPajama-INCITE-Chat-7B-v0.1",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "target_modules": [
+    "query_key_value"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-400/adapter_model/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ca4efd64564e44ad8ee7e2acbbd6d7b124f503b7ca23d69f769b3111800a84f
+size 16800753

checkpoint-400/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:885928ff49bb2ff3ebc37c9ca86b9dec6e53dbce497ab8973e8cdf59b55af2c1
+size 33608197

checkpoint-400/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:049fe273917269e803183eb2146c4d054008c50f5b9a46b8f5e2039b887a6ffe
+size 18679

checkpoint-400/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7542d1515c4bea0a7e463b7d87ae1272e8c847e60369e93fb598423cd13430e5
+size 18679

checkpoint-400/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d42105e90b4b56d846bbcc1aa0f58b2aaf3c21f5b693b2b861a9eb3c2789913
+size 18679

checkpoint-400/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab7babbe0fae9b349883d2645fcdcd99df5fe64d303f8e86e4252ff5d3780f94
+size 18679

checkpoint-400/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6afb05e12ed355bfe4bb76d830192cbf5a256a5f1ea42dd8ae480a3578c9da9
+size 18679

checkpoint-400/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc40a4be6a52cee4d7658df4041e660ffa02b0d8b5bd143bb8bb397f7b71b1a5
+size 557

checkpoint-400/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:900a5ec23049aed4393fb57e3dccd03b426335b20c3b0fae68ba3491c2114549
+size 627

checkpoint-400/trainer_state.json

@@ -0,0 +1,272 @@
+{
+  "best_metric": 1.9187651872634888,
+  "best_model_checkpoint": "./lora-redpajama/checkpoint-400",
+  "epoch": 1.8306636155606406,
+  "global_step": 400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05,
+      "learning_rate": 2.9999999999999997e-05,
+      "loss": 5.6682,
+      "step": 10
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 5.9999999999999995e-05,
+      "loss": 5.1317,
+      "step": 20
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 8.999999999999999e-05,
+      "loss": 4.1627,
+      "step": 30
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00011999999999999999,
+      "loss": 3.1593,
+      "step": 40
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00015,
+      "loss": 2.6813,
+      "step": 50
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00017999999999999998,
+      "loss": 2.4024,
+      "step": 60
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00020999999999999998,
+      "loss": 2.3087,
+      "step": 70
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00023999999999999998,
+      "loss": 2.2026,
+      "step": 80
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00027,
+      "loss": 2.1257,
+      "step": 90
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003,
+      "loss": 2.118,
+      "step": 100
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0002945848375451263,
+      "loss": 2.076,
+      "step": 110
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00028916967509025267,
+      "loss": 2.0684,
+      "step": 120
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.000283754512635379,
+      "loss": 2.0212,
+      "step": 130
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.00027833935018050537,
+      "loss": 2.0192,
+      "step": 140
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00027292418772563177,
+      "loss": 1.9991,
+      "step": 150
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0002675090252707581,
+      "loss": 2.0075,
+      "step": 160
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00026209386281588447,
+      "loss": 2.0414,
+      "step": 170
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0002566787003610108,
+      "loss": 2.0048,
+      "step": 180
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.00025126353790613716,
+      "loss": 1.9604,
+      "step": 190
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.0002458483754512635,
+      "loss": 1.9739,
+      "step": 200
+    },
+    {
+      "epoch": 0.92,
+      "eval_loss": 2.0006659030914307,
+      "eval_runtime": 83.0225,
+      "eval_samples_per_second": 24.09,
+      "eval_steps_per_second": 0.602,
+      "step": 200
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.00024043321299638986,
+      "loss": 1.9856,
+      "step": 210
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.00023501805054151624,
+      "loss": 1.9604,
+      "step": 220
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.00022960288808664258,
+      "loss": 1.9357,
+      "step": 230
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.00022418772563176893,
+      "loss": 1.9783,
+      "step": 240
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.0002187725631768953,
+      "loss": 1.9581,
+      "step": 250
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.00021335740072202166,
+      "loss": 1.9507,
+      "step": 260
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.00020794223826714798,
+      "loss": 1.9258,
+      "step": 270
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.00020252707581227435,
+      "loss": 1.912,
+      "step": 280
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.0001971119133574007,
+      "loss": 1.9246,
+      "step": 290
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 0.00019169675090252705,
+      "loss": 1.9106,
+      "step": 300
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 0.00018628158844765343,
+      "loss": 1.8997,
+      "step": 310
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 0.00018086642599277977,
+      "loss": 1.8958,
+      "step": 320
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 0.00017545126353790612,
+      "loss": 1.8874,
+      "step": 330
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 0.00017003610108303247,
+      "loss": 1.8956,
+      "step": 340
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 0.00016462093862815885,
+      "loss": 1.8743,
+      "step": 350
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 0.0001592057761732852,
+      "loss": 1.875,
+      "step": 360
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 0.00015379061371841152,
+      "loss": 1.914,
+      "step": 370
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 0.0001483754512635379,
+      "loss": 1.8679,
+      "step": 380
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 0.00014296028880866424,
+      "loss": 1.8845,
+      "step": 390
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 0.00013754512635379062,
+      "loss": 1.8715,
+      "step": 400
+    },
+    {
+      "epoch": 1.83,
+      "eval_loss": 1.9187651872634888,
+      "eval_runtime": 83.4457,
+      "eval_samples_per_second": 23.968,
+      "eval_steps_per_second": 0.599,
+      "step": 400
+    }
+  ],
+  "max_steps": 654,
+  "num_train_epochs": 3,
+  "total_flos": 4.15874362499924e+17,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-400/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e536f96c30f2c2d7847620d7ea3b09863677cb114362f51ccee9bbaba571a29
+size 3963

checkpoint-600/adapter_model/adapter_config.json

@@ -0,0 +1,16 @@
+{
+  "base_model_name_or_path": "togethercomputer/RedPajama-INCITE-Chat-7B-v0.1",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "target_modules": [
+    "query_key_value"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-600/adapter_model/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fd971104b624562910ae553cd5d59520e095baf56a806e39527f7c77511e47c
+size 16800753

checkpoint-600/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e96780f9347f9d2cfdbdfd7742dd5331b237eb1fc63ecd87a422d8fc5cddd75
+size 33608197

checkpoint-600/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72683c29d6da8f78daa9c9233473be198ed2bec08989bb1d98843b1554307bed
+size 18679

checkpoint-600/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5e4e97771a7b92845ffc6267b2ffdc66a7c8e213c7b2dc29168ca0f3a53869b
+size 18679

checkpoint-600/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:761e3e1fceaeb413e2364ed5289960988d7e0f7c3769b1fed34907fb49168fd2
+size 18679

checkpoint-600/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbef43de55881769b266b20ffbed5ffcd4257e51264e9fa29735fa46c9fbb5f6
+size 18679

checkpoint-600/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6319b294ed4fc4a02593a2c978f8f8794f82d203f85e560f5b7cc5ec3e0ecf78
+size 18679

checkpoint-600/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5dc9eacfeb00bd0bfeb98934a2309be01be65b288e0d747bbfc423b32679169f
+size 557

checkpoint-600/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:926c30c8e047c3e78553036f231b6fc7cd2b592198516d3ee1e0875dff68cacf
+size 627

checkpoint-600/trainer_state.json

@@ -0,0 +1,400 @@
+{
+  "best_metric": 1.8858510255813599,
+  "best_model_checkpoint": "./lora-redpajama/checkpoint-600",
+  "epoch": 2.745995423340961,
+  "global_step": 600,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05,
+      "learning_rate": 2.9999999999999997e-05,
+      "loss": 5.6682,
+      "step": 10
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 5.9999999999999995e-05,
+      "loss": 5.1317,
+      "step": 20
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 8.999999999999999e-05,
+      "loss": 4.1627,
+      "step": 30
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00011999999999999999,
+      "loss": 3.1593,
+      "step": 40
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00015,
+      "loss": 2.6813,
+      "step": 50
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00017999999999999998,
+      "loss": 2.4024,
+      "step": 60
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00020999999999999998,
+      "loss": 2.3087,
+      "step": 70
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00023999999999999998,
+      "loss": 2.2026,
+      "step": 80
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00027,
+      "loss": 2.1257,
+      "step": 90
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003,
+      "loss": 2.118,
+      "step": 100
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0002945848375451263,
+      "loss": 2.076,
+      "step": 110
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00028916967509025267,
+      "loss": 2.0684,
+      "step": 120
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.000283754512635379,
+      "loss": 2.0212,
+      "step": 130
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.00027833935018050537,
+      "loss": 2.0192,
+      "step": 140
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00027292418772563177,
+      "loss": 1.9991,
+      "step": 150
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0002675090252707581,
+      "loss": 2.0075,
+      "step": 160
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00026209386281588447,
+      "loss": 2.0414,
+      "step": 170
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0002566787003610108,
+      "loss": 2.0048,
+      "step": 180
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.00025126353790613716,
+      "loss": 1.9604,
+      "step": 190
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.0002458483754512635,
+      "loss": 1.9739,
+      "step": 200
+    },
+    {
+      "epoch": 0.92,
+      "eval_loss": 2.0006659030914307,
+      "eval_runtime": 83.0225,
+      "eval_samples_per_second": 24.09,
+      "eval_steps_per_second": 0.602,
+      "step": 200
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.00024043321299638986,
+      "loss": 1.9856,
+      "step": 210
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.00023501805054151624,
+      "loss": 1.9604,
+      "step": 220
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.00022960288808664258,
+      "loss": 1.9357,
+      "step": 230
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.00022418772563176893,
+      "loss": 1.9783,
+      "step": 240
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.0002187725631768953,
+      "loss": 1.9581,
+      "step": 250
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.00021335740072202166,
+      "loss": 1.9507,
+      "step": 260
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.00020794223826714798,
+      "loss": 1.9258,
+      "step": 270
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.00020252707581227435,
+      "loss": 1.912,
+      "step": 280
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.0001971119133574007,
+      "loss": 1.9246,
+      "step": 290
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 0.00019169675090252705,
+      "loss": 1.9106,
+      "step": 300
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 0.00018628158844765343,
+      "loss": 1.8997,
+      "step": 310
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 0.00018086642599277977,
+      "loss": 1.8958,
+      "step": 320
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 0.00017545126353790612,
+      "loss": 1.8874,
+      "step": 330
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 0.00017003610108303247,
+      "loss": 1.8956,
+      "step": 340
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 0.00016462093862815885,
+      "loss": 1.8743,
+      "step": 350
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 0.0001592057761732852,
+      "loss": 1.875,
+      "step": 360
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 0.00015379061371841152,
+      "loss": 1.914,
+      "step": 370
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 0.0001483754512635379,
+      "loss": 1.8679,
+      "step": 380
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 0.00014296028880866424,
+      "loss": 1.8845,
+      "step": 390
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 0.00013754512635379062,
+      "loss": 1.8715,
+      "step": 400
+    },
+    {
+      "epoch": 1.83,
+      "eval_loss": 1.9187651872634888,
+      "eval_runtime": 83.4457,
+      "eval_samples_per_second": 23.968,
+      "eval_steps_per_second": 0.599,
+      "step": 400
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 0.00013212996389891696,
+      "loss": 1.8722,
+      "step": 410
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 0.0001267148014440433,
+      "loss": 1.8782,
+      "step": 420
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 0.00012129963898916966,
+      "loss": 1.8651,
+      "step": 430
+    },
+    {
+      "epoch": 2.01,
+      "learning_rate": 0.00011588447653429602,
+      "loss": 1.8639,
+      "step": 440
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 0.00011046931407942237,
+      "loss": 1.8544,
+      "step": 450
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 0.00010505415162454872,
+      "loss": 1.8086,
+      "step": 460
+    },
+    {
+      "epoch": 2.15,
+      "learning_rate": 9.963898916967508e-05,
+      "loss": 1.8364,
+      "step": 470
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 9.422382671480144e-05,
+      "loss": 1.8745,
+      "step": 480
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 8.880866425992779e-05,
+      "loss": 1.8652,
+      "step": 490
+    },
+    {
+      "epoch": 2.29,
+      "learning_rate": 8.339350180505415e-05,
+      "loss": 1.8381,
+      "step": 500
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 7.797833935018049e-05,
+      "loss": 1.8419,
+      "step": 510
+    },
+    {
+      "epoch": 2.38,
+      "learning_rate": 7.256317689530685e-05,
+      "loss": 1.8665,
+      "step": 520
+    },
+    {
+      "epoch": 2.43,
+      "learning_rate": 6.71480144404332e-05,
+      "loss": 1.8074,
+      "step": 530
+    },
+    {
+      "epoch": 2.47,
+      "learning_rate": 6.173285198555956e-05,
+      "loss": 1.8404,
+      "step": 540
+    },
+    {
+      "epoch": 2.52,
+      "learning_rate": 5.6317689530685916e-05,
+      "loss": 1.8357,
+      "step": 550
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 5.090252707581227e-05,
+      "loss": 1.8223,
+      "step": 560
+    },
+    {
+      "epoch": 2.61,
+      "learning_rate": 4.548736462093862e-05,
+      "loss": 1.8599,
+      "step": 570
+    },
+    {
+      "epoch": 2.65,
+      "learning_rate": 4.007220216606498e-05,
+      "loss": 1.8284,
+      "step": 580
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 3.4657039711191336e-05,
+      "loss": 1.871,
+      "step": 590
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 2.9241877256317685e-05,
+      "loss": 1.8523,
+      "step": 600
+    },
+    {
+      "epoch": 2.75,
+      "eval_loss": 1.8858510255813599,
+      "eval_runtime": 83.601,
+      "eval_samples_per_second": 23.923,
+      "eval_steps_per_second": 0.598,
+      "step": 600
+    }
+  ],
+  "max_steps": 654,
+  "num_train_epochs": 3,
+  "total_flos": 6.234403544225546e+17,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-600/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e536f96c30f2c2d7847620d7ea3b09863677cb114362f51ccee9bbaba571a29
+size 3963