Training in progress, step 1900, checkpoint

last-checkpoint/README.md

@@ -201,19 +201,7 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
 ## Training procedure
 
 
-The following `bitsandbytes` quantization config was used during training:
-- quant_method: bitsandbytes
-- load_in_8bit: False
-- load_in_4bit: True
-- llm_int8_threshold: 6.0
-- llm_int8_skip_modules: None
-- llm_int8_enable_fp32_cpu_offload: False
-- llm_int8_has_fp16_weight: False
-- bnb_4bit_quant_type: nf4
-- bnb_4bit_use_double_quant: True
-- bnb_4bit_compute_dtype: float16
-
 ### Framework versions
 
 
-- PEFT 0.6.0.dev0
+- PEFT 0.6.0

last-checkpoint/adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4d45db665dd61cf0b6b6c28a27c5cceb5550819457f7c9a4ac5d7e2bd6a4ab6
+oid sha256:bdfe09cab2aff62aca857964575ca03366c4ebc12dbf03ef7ddb00734bf8bf8e
 size 50349441

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfd1ba7d57b14e8adbac3874aa7b89e93f5ee2d0bcd59860947ea69f3e387a23
-size 100693001
+oid sha256:daa64d5ba82fa546d882dc9dce9b736527998c5935371e0b2ffc56cc6fd5c305
+size 100691721

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1389c8fb4da5b08654d5ecff1c857ae43115866bad194f9289834fc2a0b6a9c8
+oid sha256:4fbdd2b971dfbcc7cf5454c92a80f7cd63b0ae56a21c3ba0214c0de0e3064545
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0410ad60e6d0138b921a03b0a3e367fd27c6ab07cb9a5006fcb66ea8e5bbacc4
+oid sha256:b2d4b4cadcabd3e17adcc39c43d8312038a1f5c7f53125f288ba4de5ed25396b
 size 627

last-checkpoint/special_tokens_map.json

@@ -1,6 +1,24 @@
 {
-  "bos_token": "<|endoftext|>",
-  "eos_token": "<|endoftext|>",
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "pad_token": "<|endoftext|>",
-  "unk_token": "<|endoftext|>"
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

last-checkpoint/tokenizer.json

@@ -1,6 +1,11 @@
 {
   "version": "1.0",
-  "truncation": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 512,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
   "padding": null,
   "added_tokens": [
     {

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.5018609762191772,
-  "best_model_checkpoint": "./outputs/checkpoint-1700",
-  "epoch": 1.238615664845173,
+  "best_metric": 1.4871549606323242,
+  "best_model_checkpoint": "./outputs/checkpoint-1800",
+  "epoch": 1.3846994535519126,
   "eval_steps": 100,
-  "global_step": 1700,
+  "global_step": 1900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -245,13 +245,41 @@
       "eval_samples_per_second": 43.536,
       "eval_steps_per_second": 5.447,
       "step": 1700
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 0.0002,
+      "loss": 1.4781,
+      "step": 1800
+    },
+    {
+      "epoch": 1.31,
+      "eval_loss": 1.4871549606323242,
+      "eval_runtime": 148.0177,
+      "eval_samples_per_second": 42.387,
+      "eval_steps_per_second": 5.303,
+      "step": 1800
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 0.0002,
+      "loss": 1.4858,
+      "step": 1900
+    },
+    {
+      "epoch": 1.38,
+      "eval_loss": 1.498619794845581,
+      "eval_runtime": 133.9486,
+      "eval_samples_per_second": 46.839,
+      "eval_steps_per_second": 5.86,
+      "step": 1900
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.0135854358789325e+17,
+  "total_flos": 1.1326135108192666e+17,
   "trial_name": null,
   "trial_params": null
 }

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5641e8a6689f7acd324a9f463af2ea7fb0e928566e361888ca8bcd1f82571899
+oid sha256:01ce1b3e35021f8f6dfd4d75b8f2f8de9073bd529f840d1746890d9de9ab9328
 size 4155